© 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. 199417
    Prev
    Next
    INDEX
    Explanations

    threatening teachers

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

    social support or loneliness

    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
     sü
    0.49
    Ĭ
    0.49
     impediments
    0.48
     bronce
    0.47
    IZONTAL
    0.47
     adicional
    0.46
     개선
    0.45
     welds
    0.45
     impedir
    0.45
     bilhões
    0.44
    POSITIVE LOGITS
    tileSize
    0.51
    Tag
    0.49
    ват
    0.49
    所で
    0.49
    舗
    0.47
     جی
    0.46
    。「
    0.45
     ಕನ
    0.45
    报
    0.45
    انی
    0.45
    Activations Density 0.000%

    No Known Activations