© 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. 149045
    Prev
    Next
    INDEX
    Explanations

    insert module, backtrack, lookup

    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
     copil
    0.67
    ంత్ర
    0.62
    WithOptions
    0.62
    鈐
    0.62
    γγ
    0.61
     बालक
    0.61
     AI
    0.61
    Tart
    0.60
    鱈
    0.59
     puno
    0.59
    POSITIVE LOGITS
     நடைபெற்ற
    0.69
     कट
    0.66
    পড়
    0.65
     رولی
    0.65
     upay
    0.64
    footer
    0.63
     '//
    0.63
     നടന്ന
    0.61
    tend
    0.60
     Slider
    0.60
    Activations Density 0.005%

    No Known Activations