© 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-262K
    7. 148992
    Prev
    Next
    INDEX
    Explanations

    biggest release

    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
    鴎
    0.74
     closets
    0.73
    Expand
    0.73
     Continue
    0.72
     Expand
    0.72
     activities
    0.69
     expanding
    0.69
     Condensed
    0.67
     needs
    0.67
    Continue
    0.66
    POSITIVE LOGITS
    梅里
    0.88
    특
    0.86
    glo
    0.83
    Blu
    0.77
     특
    0.74
    oller
    0.72
    背景
    0.72
    olino
    0.71
    awia
    0.71
    anny
    0.70
    Activations Density 0.000%

    No Known Activations