© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11928
    Prev
    Next
    INDEX
    Explanations

    adding information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    КА
    1.02
    يع
    0.96
     the
    0.95
     idioms
    0.94
    )}
    0.91
    )}.
    0.89
    ئة
    0.88
     a
    0.88
    ﺮ
    0.88
    symbols
    0.88
    POSITIVE LOGITS
    en
    1.22
     있다면
    1.09
    已经
    1.08
     wouldn
    1.07
    in
    1.04
     அதை
    1.04
    didn
    1.03
     هناك
    1.00
     Importantly
    0.99
     doesn
    0.95
    Activations Density 0.424%

    No Known Activations