© 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. 118687
    Prev
    Next
    INDEX
    Explanations

    code, names, and lists

    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
     as
    -1.26
     in
    -1.06
     it
    -1.03
     if
    -0.98
    <h4>
    -0.96
     has
    -0.93
     with
    -0.91
     cobr
    -0.91
     going
    -0.88
     hoping
    -0.88
    POSITIVE LOGITS
     ACB
    0.97
     বল
    0.94
    ╩
    0.93
    ________,
    0.93
     }.
    0.89
    "};
    0.89
    ärer
    0.88
     warung
    0.88
     solch
    0.88
    Groet
    0.86
    Activations Density 0.007%

    No Known Activations