© 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. 2172
    Prev
    Next
    INDEX
    Explanations

    Related Art

    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
     rectangle
    -0.74
    register
    -0.73
    esi
    -0.72
     SERVICE
    -0.71
     sud
    -0.70
     Highland
    -0.68
    щ
    -0.68
    Register
    -0.68
     среднем
    -0.68
    registry
    -0.67
    POSITIVE LOGITS
     Lush
    0.71
     creating
    0.68
    ÁF
    0.65
     ổ
    0.65
     satuan
    0.63
    ఉ
    0.63
    GetCurrent
    0.63
     Creating
    0.62
     took
    0.62
    lush
    0.62
    Activations Density 0.090%

    No Known Activations