© 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. 128490
    Prev
    Next
    INDEX
    Explanations

    Differentiated, Current Blog

    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
     and
    -2.61
    </b>
    -2.11
    s
    -2.02
     by
    -1.80
     in
    -1.72
    órmulas
    -1.63
    this
    -1.55
    <i>
    -1.54
     this
    -1.53
     leaders
    -1.52
    POSITIVE LOGITS
     continúas
    2.03
     Anſ
    1.90
    狃
    1.84
    蜮
    1.84
    锨
    1.80
    ⎻
    1.79
    嵛
    1.73
    皷
    1.72
    '].
    1.70
    ⎆
    1.70
    Activations Density 0.000%

    No Known Activations