© 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. 17-GEMMASCOPE-2-RES-16K
    7. 6842
    Prev
    Next
    INDEX
    Explanations

    selecting columns or properties

    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
    opération
    0.95
    sommets
    0.93
    counterx
    0.93
     சம
    0.93
     последствия
    0.93
    RZ
    0.92
    🤕
    0.91
    $",
    0.91
    を実行
    0.90
    hero
    0.90
    POSITIVE LOGITS
     desirable
    0.90
    ียบ
    0.89
    FormBorderStyle
    0.88
     conspicuous
    0.88
     appearance
    0.85
    Cited
    0.82
     Erschein
    0.81
    สนใจ
    0.80
     unusual
    0.79
     interesting
    0.79
    Activations Density 0.074%

    No Known Activations