© 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. 1940
    Prev
    Next
    INDEX
    Explanations

    lists and explanations

    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
    丁目
    -0.88
     अर्थ
    -0.77
    ጋ
    -0.75
    Vegeu
    -0.74
    ச
    -0.74
    menschen
    -0.73
     AllMovie
    -0.73
     стр
    -0.73
     vývoj
    -0.72
     Suzuki
    -0.71
    POSITIVE LOGITS
     Appreciation
    0.81
     appreciation
    0.78
    VITA
    0.78
     AFS
    0.77
    緞
    0.74
    bonus
    0.73
    Bonus
    0.73
     GAIN
    0.72
    кро
    0.72
    IDAS
    0.71
    Activations Density 0.000%

    No Known Activations