© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3254
    Prev
    Next
    INDEX
    Explanations

    html page title

    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_16_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
    ン
    1.67
    ن
    1.31
    न
    1.27
    Н
    1.14
    ア
    1.11
    아
    1.11
     crayons
    1.10
    ת
    1.07
    น
    1.05
    Я
    1.05
    POSITIVE LOGITS
    é
    1.05
    </
    1.04
     for
    0.97
     in
    0.91
    dır
    0.89
    da
    0.89
    í
    0.89
    koľ
    0.82
    ونها
    0.81
    ící
    0.78
    Activations Density 0.005%

    No Known Activations