© 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. 67516
    Prev
    Next
    INDEX
    Explanations

    injury

    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
    떳
    -3.83
    /
    -2.78
    珢
    -2.59
    ()){
    -2.58
    敉
    -2.53
    as
    -2.52
    of
    -2.45
    ቍ
    -2.42
    剮
    -2.41
    ጺ
    -2.38
    POSITIVE LOGITS
     zwanzig
    2.86
    渽
    2.80
    蟜
    2.78
    1
    2.64
    .
    2.63
    ዬ
    2.52
     aprecia
    2.50
     saranno
    2.48
     preguntar
    2.44
     ursprüng
    2.36
    Activations Density 0.015%

    No Known Activations