© 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. 203593
    Prev
    Next
    INDEX
    Explanations

    swimming classes, making it, could knock, left Fischer, notice the

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

    spoken utterances or foreign words

    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
     et
    0.54
     mkdir
    0.52
     ló
    0.52
     sum
    0.48
     millis
    0.48
    垫
    0.47
     cli
    0.47
     cone
    0.47
    tc
    0.47
     mason
    0.47
    POSITIVE LOGITS
    యితే
    0.58
    ляется
    0.54
    থেষ্ট
    0.48
    Ϝ
    0.48
     reemplazar
    0.48
     इकोनॉ
    0.47
     আশেপাশে
    0.46
     perdagangan
    0.46
     торговли
    0.45
    ClearedBy
    0.45
    Activations Density 0.001%

    No Known Activations