© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53748
    Prev
    Next
    INDEX
    Explanations

    letter choice

    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
    ྪ
    0.47
    emptyDict
    0.47
    impanan
    0.45
    厶
    0.45
    |");
    0.44
    Concini
    0.44
    Departamento
    0.43
    செய
    0.42
    OUBLE
    0.42
     리뷰
    0.42
    POSITIVE LOGITS
    ;
    0.53
     animals
    0.50
    a
    0.50
     a
    0.47
     animal
    0.46
    b
    0.46
     schw
    0.46
     kaum
    0.46
    dale
    0.45
     druk
    0.45
    Activations Density 0.003%

    No Known Activations