© 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. 128964
    Prev
    Next
    INDEX
    Explanations

    want or need

    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
    摃
    -2.64
    觧
    -2.33
    寕
    -2.31
     disposto
    -2.28
     剧照
    -2.27
    ㈲
    -2.25
    葙
    -2.22
     cittadino
    -2.22
     realizacji
    -2.20
    ၟ
    -2.16
    POSITIVE LOGITS
     he
    2.39
    ↵↵
    2.05
    忖
    1.96
     
    1.95
    してます
    1.88
     certes
    1.88
     или
    1.85
     нужно
    1.79
     to
    1.78
     она
    1.76
    Activations Density 0.023%

    No Known Activations