© 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. 20544
    Prev
    Next
    INDEX
    Explanations

    names and descriptors

    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
     Esa
    0.45
     商品
    0.45
     Kein
    0.45
    writeValue
    0.43
     Meal
    0.42
     Restaurant
    0.41
     Downtown
    0.41
     "$
    0.40
     mañana
    0.40
     Chia
    0.40
    POSITIVE LOGITS
    ENCIA
    0.43
    STOCK
    0.40
    lide
    0.38
     surveyed
    0.38
    ate
    0.37
    MOT
    0.36
    atele
    0.36
    ATE
    0.36
     survey
    0.36
     surveyors
    0.36
    Activations Density 0.002%

    No Known Activations