© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5254
    Prev
    Next
    INDEX
    Explanations

    caveats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     lignes
    1.03
     affaires
    0.96
    НЕ
    0.87
    िये
    0.86
     vieille
    0.86
    ➜
    0.84
     linee
    0.83
     Prosec
    0.82
    ื้น
    0.81
     Dyer
    0.80
    POSITIVE LOGITS
    itating
    0.95
    eit
    0.95
    room
    0.93
    楣
    0.90
     consistently
    0.90
    েজ
    0.88
    ण्य
    0.88
    รียน
    0.88
     Deeds
    0.88
    waitFor
    0.88
    Activations Density 0.083%

    No Known Activations