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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118720
    Prev
    Next
    INDEX
    Explanations

    action verbs and context

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     failings
    -1.67
    ve
    -1.34
    y
    -1.34
    e
    -1.27
     workings
    -1.25
    ings
    -1.25
     glowing
    -1.23
    浪费
    -1.23
    ver
    -1.22
    ish
    -1.22
    POSITIVE LOGITS
     Hivatalos
    1.53
     oneself
    1.38
     esqueleto
    1.34
     the
    1.33
     ujar
    1.23
     rękaw
    1.19
     tył
    1.16
     our
    1.16
     of
    1.16
     semoga
    1.15
    Activations Density 0.288%

    No Known Activations