© 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. 34759
    Prev
    Next
    INDEX
    Explanations

    commercial, episodes, trials, destinations

    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
     poter
    1.18
    汥
    1.17
     Pea
    1.16
    SAL
    1.14
     sociale
    1.13
     Lê
    1.13
     seria
    1.13
     accad
    1.13
    the
    1.12
     mostra
    1.09
    POSITIVE LOGITS
    น
    1.44
    مي
    1.34
    ли
    1.33
    ं
    1.26
    ام
    1.25
     outperform
    1.21
    ું
    1.18
    erView
    1.17
    ื่อง
    1.16
    بير
    1.16
    Activations Density 0.001%

    No Known Activations