© 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. 13395
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

    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
    传统
    0.43
     ключе
    0.42
     爱
    0.41
     Affordable
    0.41
    蚬
    0.40
    राजा
    0.39
     Де
    0.39
    蜒
    0.39
     Hacienda
    0.39
     मिताली
    0.39
    POSITIVE LOGITS
    したがって
    0.37
     disturbance
    0.36
     voltages
    0.36
    していますが
    0.35
     indeterm
    0.35
     irritation
    0.35
    DBGPRINT
    0.35
     belast
    0.34
     proteins
    0.34
     oscillations
    0.32
    Activations Density 0.119%

    No Known Activations