© 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. 22-GEMMASCOPE-RES-131K
    7. 34891
    Prev
    Next
    INDEX
    Explanations

    android.state_

    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_22/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
     those
    -0.92
     others
    -0.88
    Bek
    -0.81
     케
    -0.81
     jamais
    -0.77
     fellow
    -0.76
    Celebr
    -0.75
    tableLayoutPanel
    -0.74
    亲爱的
    -0.74
    適量
    -0.73
    POSITIVE LOGITS
    СТВО
    0.75
    Utilization
    0.74
     Exped
    0.73
     тыс
    0.73
    ラウンド
    0.72
     apasion
    0.71
    ∣
    0.71
     отно
    0.70
     
    0.70
    CharField
    0.69
    Activations Density 0.004%

    No Known Activations