© 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. 129362
    Prev
    Next
    INDEX
    Explanations

    middle name, first name, street

    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
     on
    -1.00
    bezpiecz
    -0.92
     飛
    -0.86
    
    -0.85
    Selection
    -0.85
     reliable
    -0.82
     ibland
    -0.82
    也
    -0.82
    LoL
    -0.82
    TABLE
    -0.82
    POSITIVE LOGITS
    恚
    1.08
    を追加
    1.04
    楽曲
    0.91
    するか
    0.90
     clutter
    0.90
     terreno
    0.90
     Александра
    0.89
    小さく
    0.88
     generell
    0.88
     optionally
    0.88
    Activations Density 0.003%

    No Known Activations