© 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. 12-GEMMASCOPE-2-RES-262K
    4. 41217
    Prev
    Next
    INDEX
    Explanations

    simple, patient, minded

    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
    ated
    1.30
    minster
    1.22
    ized
    1.19
    :
    1.17
    ordine
    1.14
    ing
    1.11
    heastern
    1.10
    ier
    1.09
    ist
    1.08
     Dris
    1.07
    POSITIVE LOGITS
    ckte
    1.34
     chút
    1.31
    م
    1.29
    )";
    1.24
    )';
    1.24
     toutefois
    1.21
     Presidents
    1.20
    }=$
    1.19
     ибо
    1.18
    ㍍
    1.14
    Activations Density 0.000%

    No Known Activations