Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 149286
    Prev
    Next
    INDEX
    Explanations

    open formats, direct patient, pre-star

    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
     भ्रमण
    0.72
    Reference
    0.69
    లం
    0.69
     जला
    0.68
    ွား
    0.68
    Center
    0.68
    ρωση
    0.68
    粛
    0.67
    ={}
    0.67
    Able
    0.67
    POSITIVE LOGITS
     mostly
    0.91
    mostly
    0.82
     Mostly
    0.81
     testator
    0.69
    ॉ
    0.67
     হাইক
    0.65
    кре
    0.64
     पार्थ
    0.63
     বয়সী
    0.63
    Mostly
    0.62
    Activations Density 0.001%

    No Known Activations