© 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. 9-GEMMASCOPE-2-RES-16K
    7. 1555
    Prev
    Next
    INDEX
    Explanations

    in a, an, several, seconds, size

    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_9_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
    volvement
    1.52
    ر
    1.39
    ции
    1.35
    forcement
    1.34
     việc
    1.33
    󠁧
    1.30
    сти
    1.30
     vivo
    1.29
    cedent
    1.29
    ţă
    1.28
    POSITIVE LOGITS
    g
    1.81
    س
    1.66
    k
    1.65
    क
    1.54
    tio
    1.49
    О
    1.46
    da
    1.46
    ك
    1.44
    d
    1.40
    для
    1.37
    Activations Density 0.277%

    No Known Activations