© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39875
    Prev
    Next
    INDEX
    Explanations

    occurrence

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags the single longest token in each text segment.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the end of a sentence or paragraph in formal or technical writing contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    the head noun of a noun phrase, especially when it serves as the object after prepositions or function-word modifiers (e.g., “before/after/with/of/to”).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -2.13
     espectadores
    -1.10
    tienen
    -1.05
     csomag
    -1.05
    hellip
    -1.03
     terhadap
    -1.01
     cuello
    -1.00
    岽
    -1.00
    heu
    -1.00
    鸶
    -0.99
    POSITIVE LOGITS
     to
    1.21
     occurring
    1.02
     occurrence
    0.98
     happening
    0.91
     happen
    0.91
     existence
    0.90
    chnet
    0.90
     occur
    0.90
    сында
    0.89
     happenings
    0.88
    Activations Density 0.094%

    No Known Activations