© 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. 115041
    Prev
    Next
    INDEX
    Explanations

    concealed, toothbrush, surprise, face, guest

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

    contrasting states or options

    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
    T
    0.47
    M
    0.46
    K
    0.46
    H
    0.45
    con
    0.45
    est
    0.42
    ver
    0.42
    inary
    0.42
    ，
    0.42
    。。。
    0.41
    POSITIVE LOGITS
     результат
    0.50
     Unterschiede
    0.47
    ዴት
    0.47
     curviliné
    0.45
     hasilnya
    0.45
    多様
    0.44
     variado
    0.44
    дьми
    0.43
     paradox
    0.43
     cuis
    0.43
    Activations Density 0.000%

    No Known Activations