© 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. 126475
    Prev
    Next
    INDEX
    Explanations

    movie review genre

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

    dating sim

    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
    렸
    0.51
    utm
    0.46
    ariş
    0.46
    Ordinal
    0.45
    Bombay
    0.45
    vary
    0.45
     источ
    0.45
     채
    0.45
     몸
    0.45
     นั้น
    0.45
    POSITIVE LOGITS
    とその
    0.50
     rented
    0.47
    <0xBF>
    0.47
    と比較
    0.47
    ンスター
    0.46
    列表
    0.46
     Candid
    0.46
     Corner
    0.45
     genre
    0.44
     corner
    0.43
    Activations Density 0.000%

    No Known Activations