© 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. 34-GEMMASCOPE-RES-131K
    7. 50502
    Prev
    Next
    INDEX
    Explanations

    predict or detect actions and their consequences

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

    The neuron fires strongly on content-bearing tokens (nouns, verbs, adjectives, etc.) rather than on common function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    though
    -1.22
     garder
    -1.21
    Though
    -1.19
     though
    -1.11
     döner
    -1.08
     inten
    -1.07
     cca
    -1.05
     тща
    -1.04
    یکه
    -1.02
    ciach
    -1.02
    POSITIVE LOGITS
    restes
    1.04
     interspersed
    1.04
     there
    1.00
     difficult
    1.00
     without
    0.96
    ̵
    0.96
     here
    0.95
     analyzes
    0.94
     Perhaps
    0.93
    aughty
    0.91
    Activations Density 0.009%

    No Known Activations