© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118790
    Prev
    Next
    INDEX
    Explanations

    re- prefix 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
     continues
    -0.92
     may
    -0.82
     both
    -0.79
     almost
    -0.77
    漁港
    -0.76
     add
    -0.73
     in
    -0.72
     maintains
    -0.72
     promote
    -0.71
     only
    -0.70
    POSITIVE LOGITS
    mavi
    0.82
    ごとの
    0.82
     beneficiario
    0.81
    statements
    0.81
    leece
    0.80
    ORIES
    0.79
     centaines
    0.78
    odorant
    0.77
    portes
    0.77
    cries
    0.77
    Activations Density 0.042%

    No Known Activations