© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2198
    Prev
    Next
    INDEX
    Explanations

    python class method self

    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_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
    выше
    0.69
     bás
    0.67
    輔
    0.66
    如果不
    0.66
    定义的
    0.64
     النها
    0.64
    ᑲ
    0.63
    周期
    0.63
    tmpobj
    0.63
    ormap
    0.62
    POSITIVE LOGITS
    unused
    0.70
    UNUSED
    0.67
     args
    0.65
    argv
    0.64
    teenth
    0.64
    ตัวเอง
    0.63
     argc
    0.63
     gar
    0.63
    Args
    0.62
    )
    0.61
    Activations Density 0.172%

    No Known Activations