© 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. 77600
    Prev
    Next
    INDEX
    Explanations

    various, A, side, finished, same, thing

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

    don't worry about stats

    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
    र्मेंद्र
    0.54
    只见
    0.49
    મિંગ
    0.49
    Imagenes
    0.49
    全球
    0.48
    纠
    0.48
    クリ
    0.47
    شركة
    0.47
    锲
    0.47
    夰
    0.47
    POSITIVE LOGITS
    iem
    0.54
    antal
    0.54
    iev
    0.52
    ss
    0.50
    adio
    0.50
    ied
    0.49
    uch
    0.49
     interne
    0.49
    inna
    0.49
    ond
    0.49
    Activations Density 0.002%

    No Known Activations