© 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. 112604
    Prev
    Next
    INDEX
    Explanations

    lower or fewer amounts

    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
     (>
    -1.71
     Undoubtedly
    -1.70
     Todas
    -1.64
     Somewhat
    -1.59
     Тип
    -1.59
    素晴らしい
    -1.58
     Púb
    -1.55
    nú
    -1.55
     Lleg
    -1.52
     undoubted
    -1.52
    POSITIVE LOGITS
     compared
    1.84
    。
    1.80
    t
    1.70
    ).
    1.64
    \
    1.58
    )。
    1.53
    ль
    1.47
     (<
    1.45
    崤
    1.43
    our
    1.42
    Activations Density 0.123%

    No Known Activations