© 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. 34863
    Prev
    Next
    INDEX
    Explanations

    mediast inum/inal

    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
    (\
    0.99
    =\{
    0.85
    \,.
    0.81
    scales
    0.80
    습니다
    0.75
    です
    0.75
    classes
    0.75
    (\{
    0.74
    ですし
    0.74
    `;
    0.73
    POSITIVE LOGITS
     Какие
    1.10
    et
    1.06
     ANA
    0.92
    ColorF
    0.90
     Некоторые
    0.87
    etext
    0.86
     ovih
    0.86
     Архиви
    0.86
    šću
    0.85
     honom
    0.84
    Activations Density 0.000%

    No Known Activations