© 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. 13844
    Prev
    Next
    INDEX
    Explanations

    lists of items

    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
    ভ
    2.19
    부터
    2.16
    Си
    1.90
    кого
    1.87
     Dadurch
    1.83
    "}
    1.80
    ţa
    1.80
    ța
    1.77
    Архівовано
    1.77
    हेही
    1.73
    POSITIVE LOGITS
    s
    3.10
    %)
    3.02
    noon
    2.75
    a
    2.69
    ه
    2.65
    ה
    2.45
    o
    2.38
    eing
    2.33
    ו
    2.31
    oretically
    2.28
    Activations Density 0.058%

    No Known Activations