© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65060
    Prev
    Next
    INDEX
    Explanations

    specific formatting

    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
    کم
    -0.88
    今日
    -0.83
    providedIn
    -0.82
    پل
    -0.80
     PyTuple
    -0.79
    𝒹
    -0.76
    Voor
    -0.74
     Encode
    -0.73
    Soorten
    -0.73
    
    -0.73
    POSITIVE LOGITS
    wap
    0.78
     children
    0.77
    eight
    0.77
     ditemp
    0.76
     جميع
    0.76
    vements
    0.75
     höl
    0.74
     الام
    0.73
     sebelum
    0.73
    лос
    0.73
    Activations Density 0.001%

    No Known Activations