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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25855
    Prev
    Next
    INDEX
    Explanations

    completing passes

    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
    KommentareTeilen
    -0.91
    czej
    -0.79
    fct
    -0.74
    
    -0.73
    лятор
    -0.73
     WRITTEN
    -0.72
    😂
    -0.72
    Ꮧ
    -0.72
    чування
    -0.72
    parseLong
    -0.72
    POSITIVE LOGITS
     only
    0.91
     perfect
    0.85
    of
    0.83
     just
    0.81
    ̋
    0.80
     cổ
    0.79
    Յ
    0.79
     OF
    0.76
     лишь
    0.76
    Ox
    0.75
    Activations Density 0.010%

    No Known Activations