© 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. 14097
    Prev
    Next
    INDEX
    Explanations

    underwear with briefs

    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
    m
    0.52
    地方
    0.51
     occasional
    0.50
    म
    0.48
    री
    0.46
     bases
    0.46
    ਮ
    0.46
    </code>
    0.45
     oranges
    0.45
     prefers
    0.45
    POSITIVE LOGITS
     tük
    0.47
     էին
    0.46
     टूर्
    0.46
    ümer
    0.46
    óa
    0.44
     ముందు
    0.44
    蛜
    0.44
     लगा
    0.44
    icast
    0.44
    zado
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.