© 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. 149024
    Prev
    Next
    INDEX
    Explanations

    sphere and flat Earth

    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
    भोग
    0.79
    मति
    0.78
     fina
    0.72
     lov
    0.72
    ώντας
    0.71
    টিউ
    0.71
     permettra
    0.71
     못
    0.71
     uska
    0.70
     género
    0.70
    POSITIVE LOGITS
    岸
    0.77
     crafted
    0.73
     Binance
    0.71
    ynchronous
    0.70
     negotiable
    0.69
     sporadically
    0.68
     Negev
    0.68
     cornerstone
    0.67
     pegged
    0.67
     shelved
    0.65
    Activations Density 0.000%

    No Known Activations