© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11625
    Prev
    Next
    INDEX
    Explanations

    body wash or substance abuse

    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
    ar
    1.18
    ל
    1.17
    ts
    1.16
    the
    1.16
    ot
    1.05
    r
    1.05
    ار
    0.96
    to
    0.95
    or
    0.95
    ere
    0.95
    POSITIVE LOGITS
     ovu
    1.00
     Audiodate
    0.94
     undermined
    0.94
     envisage
    0.94
     aquilo
    0.89
     allerlei
    0.89
    ک
    0.88
     ovih
    0.88
     luego
    0.87
     endeav
    0.87
    Activations Density 0.000%

    No Known Activations