© 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. 40427
    Prev
    Next
    INDEX
    Explanations

    metric tons

    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
    ار
    1.38
    र
    1.26
    à
    1.23
    of
    1.20
    od
    1.16
    op
    1.08
    are
    1.08
    em
    1.07
    am
    1.02
    the
    1.01
    POSITIVE LOGITS
     Issled
    1.44
     eten
    1.27
    .。
    1.22
     başında
    1.17
    contenedor
    1.16
     volna
    1.14
     remem
    1.13
     enseñ
    1.13
     condiment
    1.13
    )_
    1.13
    Activations Density 0.004%

    No Known Activations