© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3684
    Prev
    Next
    INDEX
    Explanations

    imaginary unit and indices

    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_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
    䡛
    0.72
    ະລ
    0.68
     Menz
    0.65
    熱
    0.63
     cunt
    0.63
     чем
    0.63
    brus
    0.62
     وط
    0.62
    พลัง
    0.62
    غم
    0.62
    POSITIVE LOGITS
     i
    2.76
     İ
    2.20
    i
    2.15
    ｉ
    1.94
     í
    1.91
    イ
    1.87
    𝑖
    1.78
     イ
    1.75
     இ
    1.74
     아이
    1.74
    Activations Density 1.543%

    No Known Activations