© 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. 66364
    Prev
    Next
    INDEX
    Explanations

    to travel, just turn, female control

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

    The neuron activates most strongly on common short function words (prepositions, articles, auxiliaries, etc.).

    oai_token-act-pair · o4-miniTriggered 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
    dopodob
    -1.24
     không
    -1.08
    rufe
    -1.07
    ⇩
    -1.06
     retrouvé
    -1.00
     coloris
    -0.98
     elefante
    -0.98
     ikkje
    -0.97
    торой
    -0.97
    Perché
    -0.96
    POSITIVE LOGITS
     any
    1.55
     anyone
    1.13
     their
    1.09
     it
    1.08
     its
    1.03
    有任何
    1.01
     attempt
    1.00
     attempted
    0.96
     ext
    0.95
     n
    0.92
    Activations Density 0.032%

    No Known Activations