© 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. 110647
    Prev
    Next
    INDEX
    Explanations

    @ notices or copyright

    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
    Č
    -0.82
    ᵈ
    -0.81
     fluids
    -0.81
    Ď
    -0.79
     serum
    -0.77
    描述
    -0.77
     }}">
    -0.75
    DER
    -0.75
    macros
    -0.75
     Winning
    -0.74
    POSITIVE LOGITS
     benutzt
    0.81
    씩
    0.80
    atina
    0.79
     untersuchen
    0.79
    没人
    0.77
    多大
    0.77
     tphcm
    0.75
    ствовали
    0.75
    𒀭
    0.75
    能让
    0.74
    Activations Density 0.009%

    No Known Activations