© 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. 9526
    Prev
    Next
    INDEX
    Explanations

    under3 ratings

    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
    盉
    -1.84
    鸸
    -1.79
    鲩
    -1.67
    ྂ
    -1.61
     mistura
    -1.61
     編み
    -1.59
    犼
    -1.59
     męskie
    -1.59
     hae
    -1.59
    鹋
    -1.58
    POSITIVE LOGITS
     to
    2.06
     WITH
    2.00
     like
    1.80
     of
    1.75
    es
    1.73
     constantly
    1.71
     using
    1.65
    :
    1.64
    The
    1.63
     can
    1.63
    Activations Density 0.016%

    No Known Activations