© 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. 128612
    Prev
    Next
    INDEX
    Explanations

    goals and objectives

    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
    鬭
    -2.73
    {
    -2.69
     Your
    -2.67
    )
    -2.67
    ."
    -2.30
    where
    -2.13
     linken
    -2.13
    of
    -2.13
    っている
    -2.11
     cordón
    -2.09
    POSITIVE LOGITS
    呖
    3.55
    髕
    2.64
    ‪.‬‬
    2.52
    ଝ
    2.50
    弍
    2.48
    ⟞
    2.45
    핥
    2.45
    สำหรับ
    2.44
     ก็
    2.42
    n
    2.42
    Activations Density 0.006%

    No Known Activations