© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 7999
    Prev
    Next
    INDEX
    Explanations

    Gesprächspartner Bach Feedback Song Klassen

    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_17_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
     quelle
    0.79
     能
    0.77
     койма
    0.75
     ogni
    0.74
     النا
    0.69
     ৬
    0.69
     stá
    0.68
    ஏ
    0.68
     unele
    0.67
    żej
    0.67
    POSITIVE LOGITS
    jenigen
    0.82
    แห่ง
    0.73
    ्स
    0.72
    OfMonth
    0.70
    라인
    0.69
     गेंदों
    0.67
    munic
    0.66
    uettes
    0.66
     koji
    0.66
    extérieur
    0.65
    Activations Density 0.017%

    No Known Activations