© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 3862
    Prev
    Next
    INDEX
    Explanations

    form compound terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ak
    0.49
    on
    0.46
    א
    0.44
    িন
    0.43
    ل
    0.43
    و
    0.43
    রিষ্ঠ
    0.42
    Grid
    0.41
    meler
    0.41
    un
    0.40
    POSITIVE LOGITS
    ،
    0.68
    ，
    0.63
    、
    0.55
    。
    0.54
    '
    0.50
    ?
    0.49
    ícul
    0.48
     adhipp
    0.48
    𝟏
    0.46
    𝟐
    0.46
    Activations Density 0.919%

    No Known Activations