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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 4060
    Prev
    Next
    INDEX
    Explanations

    URL slashes

    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_22_width_65k_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
    wirkungen
    0.85
    μάτων
    0.83
     ডাউনলোড
    0.82
    らえる
    0.81
    க்ஸாண்ட
    0.79
     Ninh
    0.78
    BetMap
    0.78
     ჩ
    0.77
    配布
    0.76
     patrocin
    0.75
    POSITIVE LOGITS
    angular
    0.67
    ynos
    0.65
     strain
    0.65
     uten
    0.64
     tearing
    0.64
     ربنا
    0.63
    is
    0.63
    NO
    0.63
    isch
    0.63
    ulen
    0.62
    Activations Density 0.038%

    No Known Activations