© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12340
    Prev
    Next
    INDEX
    Explanations

    code

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    dung
    2.94
    CIÓN
    2.86
    raum
    2.80
    за
    2.77
    wv
    2.73
     isLoading
    2.72
    Recurs
    2.63
     partic
    2.61
     bijection
    2.60
    𝘫
    2.59
    POSITIVE LOGITS
     snippetHide
    3.52
    ﺮ
    3.41
    ्स
    3.16
    ورت
    2.87
    isnull
    2.84
    rawValue
    2.79
    ется
    2.76
    ی
    2.71
     wParam
    2.70
    ्मण
    2.69
    Activations Density 0.091%

    No Known Activations