© 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. 9-GEMMASCOPE-2-RES-16K
    7. 112
    Prev
    Next
    INDEX
    Explanations

    https://

    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_9_width_16k_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
    t
    1.94
    ર
    1.66
    ר
    1.63
    ânia
    1.62
    tım
    1.62
    मंगल
    1.62
    א
    1.59
     इसके
    1.58
     kuće
    1.57
    ри
    1.56
    POSITIVE LOGITS
    ://
    1.85
     '=
    1.68
     antit
    1.61
    طقة
    1.58
    ाइवेट
    1.55
    ively
    1.55
    Interested
    1.52
     aback
    1.51
     isEmpty
    1.49
     ornamental
    1.46
    Activations Density 0.466%

    No Known Activations