© 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. 17-GEMMASCOPE-2-RES-16K
    7. 5965
    Prev
    Next
    INDEX
    Explanations

    reading file paths

    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_17_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
    𝗸
    1.28
    𝗱
    1.23
    𝗲
    1.20
    ی
    1.18
    𝙀
    1.18
    𝗴
    1.12
    𝘁
    1.10
    𝗷
    1.09
    𝗘
    1.09
    𝐄
    1.06
    POSITIVE LOGITS
    uest
    1.13
     auspices
    1.02
    ;
    0.98
    cenie
    0.95
    প্রসঙ্গত
    0.94
     funcion
    0.92
    bcc
    0.92
    蜢
    0.92
    hko
    0.92
    m
    0.90
    Activations Density 0.002%

    No Known Activations