© 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. 34804
    Prev
    Next
    INDEX
    Explanations

    specific descriptions or details

    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
    Tecla
    0.49
    ᚐ
    0.46
    ‌آ
    0.46
    ENSOR
    0.44
     procede
    0.44
    statistik
    0.44
    Productos
    0.44
    Cookie
    0.44
    慜
    0.43
    Durante
    0.43
    POSITIVE LOGITS
     boarded
    0.47
     suppressed
    0.43
     topped
    0.42
    μμα
    0.41
    راضي
    0.41
     ll
    0.40
     fier
    0.40
     çat
    0.40
     beaches
    0.39
     smothered
    0.39
    Activations Density 0.003%

    No Known Activations