© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73072
    Prev
    Next
    INDEX
    Explanations

    object or data mapping

    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
    脔
    -2.72
    ⚢
    -2.44
    椹
    -2.41
    賒
    -2.41
     auffi
    -2.39
    玏
    -2.39
     炖
    -2.31
    ᯅ
    -2.28
    pecabe
    -2.23
     techniczne
    -2.19
    POSITIVE LOGITS
            
    2.91
        
    2.73
    </h1>
    2.42
    Our
    2.31
     When
    2.28
    …
    2.27
    What
    2.20
    カップ
    2.19
    How
    2.16
    <
    2.14
    Activations Density 0.001%

    No Known Activations