© 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. 120813
    Prev
    Next
    INDEX
    Explanations

    re re re re re solving

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

    minimum amount

    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
     사람들
    0.40
     సంగీ
    0.40
    [,,"
    0.39
    贩
    0.38
    들
    0.37
    Powers
    0.37
    जुर्ग
    0.37
     gebruiken
    0.37
     пси
    0.36
    ండి
    0.36
    POSITIVE LOGITS
     and
    0.65
     Ignition
    0.56
     Odessa
    0.55
     Kino
    0.55
    ニア
    0.54
     Laos
    0.53
     Alamo
    0.52
    ą
    0.51
     that
    0.51
     नाव
    0.51
    Activations Density 0.001%

    No Known Activations