© 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. 1502
    Prev
    Next
    INDEX
    Explanations

    Elysium history

    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
    nings
    0.58
    in
    0.57
    night
    0.57
    most
    0.53
    north
    0.53
    Jin
    0.53
    V
    0.53
    time
    0.52
    according
    0.52
    Forbidden
    0.52
    POSITIVE LOGITS
     singleton
    0.60
     persist
    0.48
    েদ
    0.44
     continuation
    0.44
     intakes
    0.43
     boolean
    0.42
     variant
    0.42
    堣
    0.42
     persisted
    0.41
     covariates
    0.41
    Activations Density 0.004%

    No Known Activations