© 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. 76821
    Prev
    Next
    INDEX
    Explanations

    structure and organization

    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
    br
    0.44
    0
    0.44
     récentes
    0.43
     direct
    0.42
     catheters
    0.40
     ep
    0.40
     cytochrome
    0.38
    fmt
    0.38
    snp
    0.38
    gt
    0.38
    POSITIVE LOGITS
     Infantry
    0.47
     Дже
    0.47
     Джа
    0.46
     перемен
    0.44
    umpulan
    0.44
     பொருத்த
    0.44
    厛
    0.44
     sebuah
    0.43
     прид
    0.43
     полицей
    0.43
    Activations Density 0.010%

    No Known Activations