© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1253
    Prev
    Next
    INDEX
    Explanations

    numbers and policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     (‘
    1.50
     cred
    1.33
    ële
    1.29
    めで
    1.23
    筵
    1.21
     (%
    1.20
     told
    1.17
     of
    1.16
    足を
    1.15
    ye
    1.13
    POSITIVE LOGITS
    ٥
    2.95
    ٧
    2.78
    ٦
    2.75
     абсолютно
    2.71
    كن
    2.70
    дол
    2.70
    ٣
    2.66
    رد
    2.66
    же
    2.66
     верх
    2.63
    Activations Density 0.111%

    No Known Activations