© 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
    2. Gemma-3-12B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8131
    Prev
    Next
    INDEX
    Explanations

    disclaimers or cautionary notes

    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_31_width_16k_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
    !】
    0.95
     detergent
    0.82
    ']}")
    0.80
    ']}
    0.79
     Aviv
    0.79
    ર
    0.79
     trattano
    0.76
     wirklich
    0.75
     fouled
    0.75
     forgiving
    0.75
    POSITIVE LOGITS
    </em>
    1.07
     */
    1.07
    </i>
    0.99
    There
    0.98
    This
    0.96
    The
    0.95
    Примеча
    0.94
    However
    0.92
    Note
    0.89
    Although
    0.88
    Activations Density 0.075%

    No Known Activations