© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 239132
    Prev
    Next
    INDEX
    Explanations

    view of inner or outer sole

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ಲೆಂ
    0.52
    бре
    0.51
    ГА
    0.51
    хожу
    0.51
    ಶ್ರ
    0.50
    кра
    0.50
    מ
    0.50
     فال
    0.49
    ಾನೂ
    0.49
     लिहा
    0.49
    POSITIVE LOGITS
    </th>
    0.57
     summarizes
    0.46
    escu
    0.46
    )}
    0.45
    </td>
    0.44
    ).
    0.43
    </sub>
    0.41
    FRAM
    0.41
    en
    0.40
     Sherlock
    0.40
    Activations Density 0.000%

    No Known Activations