© 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. 118858
    Prev
    Next
    INDEX
    Explanations

    chart positions and duration

    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
     with
    -0.88
     through
    -0.87
     sometimes
    -0.85
    utebol
    -0.80
     at
    -0.79
    ئيس
    -0.79
     usually
    -0.78
     or
    -0.77
     create
    -0.76
     yesterday
    -0.75
    POSITIVE LOGITS
     débris
    0.99
     peak
    0.98
     WEEKS
    0.92
     MAKING
    0.91
    Weeks
    0.90
     durer
    0.90
     chanti
    0.90
     mals
    0.89
    spent
    0.88
    וך
    0.87
    Activations Density 0.074%

    No Known Activations