© 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. 89729
    Prev
    Next
    INDEX
    Explanations

    versatile

    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
    ą
    1.06
     on
    1.03
    ır
    1.02
    на
    0.99
    cı
    0.98
     modeller
    0.97
     sebagainya
    0.95
     ਵ
    0.93
    ings
    0.91
    eda
    0.90
    POSITIVE LOGITS
    (
    1.59
     vers
    1.54
     Vers
    1.37
    Vers
    1.36
    ز
    1.35
    ر
    1.20
     VERS
    1.17
    r
    1.11
    ８
    1.11
    s
    1.09
    Activations Density 0.001%

    No Known Activations