© 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. 22-GEMMASCOPE-RES-131K
    7. 68468
    Prev
    Next
    INDEX
    Explanations

    NOTICE brief

    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
     abrazo
    -0.96
    示意图
    -0.94
    Ehrungen
    -0.92
    ちん
    -0.92
     объяс
    -0.91
     páns
    -0.90
     dáms
    -0.89
    apd
    -0.88
    ofman
    -0.88
     ſta
    -0.88
    POSITIVE LOGITS
     from
    1.06
     at
    0.96
     even
    0.93
     in
    0.90
     тільки
    0.84
     just
    0.83
     had
    0.81
    อีก
    0.81
    蜇
    0.81
    ဝ
    0.79
    Activations Density 0.001%

    No Known Activations