Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 149191
    Prev
    Next
    INDEX
    Explanations

    numbers, sleep, or chinese 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_29_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
     Geelong
    0.80
     che
    0.78
     Delivery
    0.73
     ሜ
    0.72
    wholesale
    0.71
    هما
    0.70
     চৈত
    0.70
     competit
    0.69
    todolist
    0.69
    菡
    0.69
    POSITIVE LOGITS
    osa
    0.82
    長的
    0.82
    長の
    0.81
    想象
    0.79
     توجہ
    0.77
    袴
    0.76
    想像
    0.75
    Os
    0.74
    Functions
    0.74
    长的
    0.73
    Activations Density 0.000%

    No Known Activations