© 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. 73732
    Prev
    Next
    INDEX
    Explanations

    ingenuity and innovation

    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
    to
    -2.92
    。」
    -2.28
    檮
    -2.23
    Neue
    -2.23
    谂
    -2.13
     epitome
    -2.06
    out
    -2.03
    of
    -2.03
     FIGURES
    -2.00
    筚
    -2.00
    POSITIVE LOGITS
    .
    2.59
    潆
    2.59
     of
    2.58
     también
    2.28
     displays
    2.25
    やう
    2.20
     Inſ
    2.14
     ámbitos
    2.13
     Шаг
    2.13
     Which
    2.11
    Activations Density 0.003%

    No Known Activations