© 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. 38401
    Prev
    Next
    INDEX
    Explanations

    widget properties

    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
    e
    -2.98
     we
    -2.91
    轳
    -2.47
     intend
    -2.44
    翃
    -2.38
    鈰
    -2.36
    
    -2.33
    逦
    -2.27
     effortlessly
    -2.23
     overwhelmingly
    -2.22
    POSITIVE LOGITS
    筇
    2.45
    requireNonNull
    2.30
    凩
    2.28
    な感じ
    2.27
    ﮟ
    2.20
    ጮ
    2.14
    <()>
    2.14
     和
    2.06
    ዡ
    2.06
    前来
    2.02
    Activations Density 0.013%

    No Known Activations