© 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. 143499
    Prev
    Next
    INDEX
    Explanations

    catalysts, area, longer input

    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
     Choices
    0.48
    arad
    0.46
     Styles
    0.46
    igon
    0.45
    缡
    0.45
     Pres
    0.44
     Choice
    0.44
    माण
    0.43
    oros
    0.43
    era
    0.43
    POSITIVE LOGITS
    ...*/
    0.51
    hp
    0.46
     tanta
    0.46
     eaux
    0.44
    dataframe
    0.44
     uptime
    0.43
     δε
    0.42
     nešto
    0.42
    主管部门
    0.42
     tbl
    0.42
    Activations Density 0.001%

    No Known Activations