© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 93191
    Prev
    Next
    INDEX
    Explanations

    IT must, mine looks, upside down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    у
    0.63
    от
    0.57
    ле
    0.55
    early
    0.53
    export
    0.52
    য়া
    0.52
    increased
    0.52
    a
    0.51
    Western
    0.50
    e
    0.50
    POSITIVE LOGITS
    acariy
    0.53
     Δεν
    0.46
     плате
    0.45
     μόνο
    0.44
     predecess
    0.43
     казіно
    0.43
     λογ
    0.43
     pocos
    0.42
     عالی
    0.42
     giây
    0.40
    Activations Density 0.004%

    No Known Activations