© 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. 118879
    Prev
    Next
    INDEX
    Explanations

    parts of words

    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
     this
    -1.25
     one
    -1.17
     that
    -1.16
     an
    -1.09
     another
    -1.08
     a
    -1.07
     after
    -1.07
     longstanding
    -1.05
    有一个
    -1.03
    vább
    -1.02
    POSITIVE LOGITS
     những
    2.84
     các
    2.52
     mga
    2.30
     those
    2.06
    льные
    1.71
    那些
    1.63
    Những
    1.63
     Những
    1.57
    those
    1.55
     των
    1.54
    Activations Density 0.010%

    No Known Activations