© 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. 1827
    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
    м
    3.28
    م
    3.17
    n
    2.74
    ن
    2.60
    l
    2.33
    m
    2.09
    ка
    2.03
    ર
    1.99
    nya
    1.96
    न
    1.84
    POSITIVE LOGITS
    ̣n
    2.11
    ።
    2.05
    ுகிறது
    2.03
    eat
    1.84
    გილ
    1.82
    roughly
    1.82
    heb
    1.82
    anel
    1.81
     dominions
    1.78
    तीय
    1.78
    Activations Density 0.076%

    No Known Activations