© 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. 25248
    Prev
    Next
    INDEX
    Explanations

    json configuration and code

    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
     formula
    0.47
    d
    0.45
     introduction
    0.44
     vibration
    0.42
     screw
    0.41
     gasoline
    0.41
    t
    0.40
     prove
    0.40
    ⅼ
    0.40
     obscene
    0.39
    POSITIVE LOGITS
     〢
    0.42
    隧
    0.42
    oscopes
    0.41
     współpr
    0.40
    랜드
    0.40
    HUN
    0.40
     extraer
    0.39
     Бүген
    0.39
    Region
    0.39
    缓存
    0.39
    Activations Density 0.005%

    No Known Activations