© 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. 2251
    Prev
    Next
    INDEX
    Explanations

    function argument descriptions

    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
    ن
    2.04
    ী
    1.86
    ية
    1.79
    и
    1.70
    िक
    1.68
    տ
    1.66
    ோ
    1.65
    ل
    1.65
    n
    1.60
     sluč
    1.58
    POSITIVE LOGITS
    Chorus
    1.71
    zal
    1.65
    eps
    1.64
    helm
    1.62
    chs
    1.61
     interno
    1.59
    waves
    1.56
    𝑄
    1.56
    fps
    1.54
    Especific
    1.52
    Activations Density 0.207%

    No Known Activations