© 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-65K
    7. 56918
    Prev
    Next
    INDEX
    Explanations

    loss, arXiv, OPT, East, types

    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_65k_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
    //
    0.50
    东西
    0.50
    ط
    0.47
    ي
    0.46
    的
    0.45
    كان
    0.45
    캔
    0.44
    </i>
    0.44
     interf
    0.44
    花
    0.43
    POSITIVE LOGITS
    esson
    0.53
     Whiting
    0.50
    IVIDUAL
    0.49
    U
    0.47
    ino
    0.46
     Maldonado
    0.46
    age
    0.44
    Theorem
    0.44
    hythmic
    0.44
    OPER
    0.44
    Activations Density 0.002%

    No Known Activations