© 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. 11808
    Prev
    Next
    INDEX
    Explanations

    baseline

    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
    Not in Any Lists

    No Comments

    Negative Logits
    an
    2.28
    ok
    2.08
    at
    2.03
     volna
    2.03
    ש
    2.02
     	i
    1.97
    ه
    1.92
    setTimeout
    1.90
    n
    1.84
    ول
    1.83
    POSITIVE LOGITS
    ли
    3.42
    ल
    3.22
    ك
    2.84
    т
    2.72
    า
    2.72
    าค
    2.39
    ف
    2.17
    기
    2.16
    ти
    2.11
    ル
    2.11
    Activations Density 0.060%

    No Known Activations