© 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. 14737
    Prev
    Next
    INDEX
    Explanations

    Here's

    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
    Ꭻ
    1.07
    この記事
    1.03
    𝘫
    0.97
     Elaina
    0.95
    taobao
    0.95
     uye
    0.93
    čenje
    0.93
    𝘢
    0.91
    ‘
    0.89
     acompañ
    0.89
    POSITIVE LOGITS
    :
    0.93
    at
    0.92
     hê
    0.78
    available
    0.77
     reaches
    0.76
     infin
    0.75
    ՝
    0.75
    CrossOrigin
    0.74
     softer
    0.73
    ত্ব
    0.72
    Activations Density 0.002%

    No Known Activations