© 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. 49160
    Prev
    Next
    INDEX
    Explanations

    Code Generation

    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
    '
    0.45
     trembling
    0.44
     velvety
    0.44
    לח
    0.43
     Minggu
    0.43
    ivable
    0.42
    ל
    0.42
     बंधन
    0.42
    ต
    0.41
    त
    0.41
    POSITIVE LOGITS
     telephony
    0.55
    发送
    0.53
     similaires
    0.50
     databases
    0.46
     headers
    0.45
     paging
    0.45
     aggressively
    0.44
     antennas
    0.44
     URLs
    0.44
    কমার
    0.44
    Activations Density 0.022%

    No Known Activations