© 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. 177358
    Prev
    Next
    INDEX
    Explanations

    future crime

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

    assessing interest, anxiety, intelligence

    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
    ắc
    0.54
     комнаты
    0.51
     мечта
    0.50
     serii
    0.49
    워
    0.48
     што
    0.47
     Сегодня
    0.47
    ولا
    0.47
    ట్టిన
    0.47
     корпуса
    0.46
    POSITIVE LOGITS
    DockStyle
    0.50
     mung
    0.49
    |(
    0.44
     morphological
    0.43
     prüfen
    0.41
     min
    0.41
     samtidig
    0.40
    should
    0.40
     simultaneous
    0.40
    ubah
    0.40
    Activations Density 0.000%

    No Known Activations