© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9529
    Prev
    Next
    INDEX
    Explanations

    IOI and nights

    np_acts-logits-general · gemini-2.5-flash-lite

    programming language syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coinChange
    0.45
     أهل
    0.43
    鰱
    0.43
    '।
    0.42
    getSimpleName
    0.42
    ᅡ
    0.41
    "।
    0.40
     الأش
    0.40
    㓩
    0.40
    韪
    0.40
    POSITIVE LOGITS
    常
    0.49
    inline
    0.48
    蒟
    0.48
     inline
    0.45
    mier
    0.43
    [++
    0.42
    舰
    0.42
     Re
    0.41
    ULU
    0.41
     Lu
    0.41
    Activations Density 0.002%

    No Known Activations