© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 1972
    Prev
    Next
    INDEX
    Explanations

    this followed by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     jogs
    0.81
    ല്ലാം
    0.81
     gratitude
    0.77
    ļ
    0.70
     gallons
    0.68
     exatamente
    0.67
     idols
    0.67
    asen
    0.67
     moves
    0.66
     confirmations
    0.66
    POSITIVE LOGITS
     本
    1.47
    本
    1.45
    本文
    1.40
    本次
    1.24
    今回
    1.24
    今回は
    1.23
    近年
    1.23
    本项目
    1.22
     본
    1.20
    今回の
    1.19
    Activations Density 0.131%

    No Known Activations