© 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. 200918
    Prev
    Next
    INDEX
    Explanations

    hand gestures and phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    palm position or orientation

    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
    </h3>
    0.50
    ay
    0.47
    ém
    0.47
    ल
    0.46
    ough
    0.44
    unki
    0.44
     समाधान
    0.43
    ओएस
    0.43
    ytuc
    0.43
    改善
    0.43
    POSITIVE LOGITS
     blushed
    0.51
     reqParams
    0.47
     trás
    0.47
    覤
    0.47
     fundamentos
    0.46
     drie
    0.44
     calend
    0.44
     handled
    0.43
     textAlign
    0.43
     فين
    0.43
    Activations Density 0.000%

    No Known Activations