© 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. 36612
    Prev
    Next
    INDEX
    Explanations

    evaluating proposals

    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
     množství
    0.47
    ^{-
    0.47
    平时
    0.46
    బ్బు
    0.44
     réduction
    0.43
    lients
    0.43
    LLY
    0.42
     reduce
    0.42
    Ȼ
    0.42
    äns
    0.41
    POSITIVE LOGITS
    Он
    0.52
     gastronomic
    0.45
    ඌ
    0.43
     Methods
    0.43
     Ideas
    0.42
     supermarkets
    0.42
    processable
    0.40
     investigation
    0.40
     Investigation
    0.39
     جهان
    0.39
    Activations Density 0.015%

    No Known Activations