© 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. 209912
    Prev
    Next
    INDEX
    Explanations

    Gamera, Columbian, Sax, Blade

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

    Bard and Gemini

    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
    рин
    0.48
    Pilot
    0.47
    Dun
    0.46
    鲇
    0.46
    iunea
    0.46
    중
    0.46
     applicator
    0.45
    ق
    0.45
    恽
    0.45
    ватися
    0.45
    POSITIVE LOGITS
    😈
    0.59
    👿
    0.51
    🎙
    0.46
    📏
    0.45
    ani
    0.45
     অথবা
    0.45
    👹
    0.44
    🤬
    0.44
    🥃
    0.44
     atau
    0.43
    Activations Density 0.000%

    No Known Activations