© 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. 29-GEMMASCOPE-2-RES-65K
    7. 3614
    Prev
    Next
    INDEX
    Explanations

    Polish language processing

    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_29_width_65k_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
     Ohr
    0.73
    три
    0.71
     فیصلہ
    0.69
    Ли
    0.68
     समझिए
    0.67
    Ly
    0.66
    सार
    0.66
    灭
    0.66
    Ful
    0.65
    Tiffany
    0.64
    POSITIVE LOGITS
    ę
    1.06
    ność
    1.05
    zenie
    1.03
    ności
    1.03
    czenie
    0.99
    acz
    0.97
    cze
    0.97
    nością
    0.96
    ieni
    0.95
    nict
    0.94
    Activations Density 0.010%

    No Known Activations