© 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. 148960
    Prev
    Next
    INDEX
    Explanations

    Southwest

    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
     leapt
    0.90
     leaped
    0.86
    మిక
    0.80
    Sprites
    0.80
     مرتبہ
    0.79
    ┛
    0.79
    RestorePolicy
    0.79
    utory
    0.79
     jumped
    0.78
    ald
    0.78
    POSITIVE LOGITS
     Crescent
    0.73
     ایر
    0.66
     Qu
    0.65
     stress
    0.64
     never
    0.64
     I
    0.62
     MI
    0.62
     till
    0.60
     Ir
    0.60
     G
    0.59
    Activations Density 0.011%

    No Known Activations