© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 13772
    Prev
    Next
    INDEX
    Explanations

    code comments and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    </h1>
    0.56
    </b>
    0.45
     kur
    0.41
    ATING
    0.36
     zaw
    0.36
     कुर
    0.36
     dyr
    0.36
     Formulas
    0.34
     Alleg
    0.33
     hop
    0.33
    POSITIVE LOGITS
    </em>
    0.73
    ;*/
    0.62
    ...*/
    0.61
    }*/
    0.58
    );*/
    0.57
     }*/
    0.55
    ");*/
    0.54
     */
    0.53
    </i>
    0.52
    */
    0.52
    Activations Density 0.003%

    No Known Activations