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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123366
    Prev
    Next
    INDEX
    Explanations

    foreign countries or data usage

    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
    ק
    0.55
    Joke
    0.51
    щиков
    0.50
    ورك
    0.50
    логов
    0.50
    器件
    0.49
    Listening
    0.48
    边
    0.48
    Video
    0.47
    Experiment
    0.47
    POSITIVE LOGITS
     mt
    0.45
    igay
    0.43
     ог
    0.42
     mand
    0.42
     ¥
    0.42
    ochet
    0.42
     엄
    0.42
     tul
    0.42
    pollo
    0.42
     mrs
    0.42
    Activations Density 0.003%

    No Known Activations