© 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. 10-GEMMASCOPE-RES-131K
    7. 102528
    Prev
    Next
    INDEX
    Explanations

    nicknames and associated names

    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_10/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
    镚
    -2.80
    
    -2.56
     wahre
    -2.39
     erzählt
    -2.27
    揼
    -2.22
     to
    -2.16
     erzählen
    -2.14
     menschliche
    -2.13
     endured
    -2.09
     thậm
    -2.08
    POSITIVE LOGITS
    镡
    2.45
    geſ
    2.31
    珰
    2.16
    蔸
    2.16
    d
    2.05
     disfraz
    2.03
     mijn
    2.00
    вети
    1.98
    F
    1.97
    because
    1.92
    Activations Density 0.001%

    No Known Activations