© 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. 29999
    Prev
    Next
    INDEX
    Explanations

    due process

    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
     dinast
    0.52
     TouchUtils
    0.46
    osevelt
    0.46
     kerajaan
    0.46
     analges
    0.45
     canaux
    0.45
    +++++++++#
    0.45
     renderEncoder
    0.45
     راز
    0.45
     dasar
    0.44
    POSITIVE LOGITS
    g
    0.46
    UI
    0.46
    트
    0.45
     or
    0.45
    1
    0.45
    mathrm
    0.43
     up
    0.43
     cramped
    0.43
    t
    0.43
    d
    0.43
    Activations Density 0.002%

    No Known Activations