© 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. 29-GEMMASCOPE-2-RES-65K
    7. 5155
    Prev
    Next
    INDEX
    Explanations

    command prompt

    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_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
     laptops
    0.74
    enean
    0.74
    ecek
    0.69
     computers
    0.69
     laptop
    0.67
    け
    0.67
    电脑
    0.66
    ismet
    0.66
    boss
    0.64
     гало
    0.64
    POSITIVE LOGITS
     Prompt
    1.37
    Prompt
    1.30
     prompt
    1.29
    prompt
    1.05
     window
    1.04
    Window
    0.95
    window
    0.94
     PROM
    0.93
     PRO
    0.93
    窓
    0.91
    Activations Density 0.047%

    No Known Activations