© 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-262K
    7. 35338
    Prev
    Next
    INDEX
    Explanations

    declare variables

    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_262k_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
    -
    1.60
    .
    1.39
    大
    1.27
    га
    1.13
    一块
    1.13
    。
    1.12
    ية
    1.09
    。《
    1.05
    он
    1.04
     aé
    1.03
    POSITIVE LOGITS
    ib
    1.17
    on
    1.11
    us
    1.09
    Z
    1.05
    B
    1.00
    R
    0.97
    ling
    0.96
    S
    0.95
    €™
    0.95
    V
    0.94
    Activations Density 0.007%

    No Known Activations