© 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. 3404
    Prev
    Next
    INDEX
    Explanations

    numbers and estimates

    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
     annat
    0.71
    őség
    0.67
    రం
    0.64
    garian
    0.63
    šenje
    0.61
     microbe
    0.60
    Rets
    0.59
    
    0.58
    ванович
    0.57
    osum
    0.57
    POSITIVE LOGITS
     উঠেছে
    0.83
     considerada
    0.76
     considerado
    0.75
     enorme
    0.75
     Children
    0.74
     estimados
    0.74
     नाखून
    0.73
     মহিলা
    0.72
    Демо
    0.70
    стр
    0.70
    Activations Density 0.034%

    No Known Activations