© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7362
    Prev
    Next
    INDEX
    Explanations

    ICD coding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     porod
    1.69
    y
    1.37
     ey
    1.35
    gue
    1.30
    kaj
    1.29
     vod
    1.29
    ous
    1.26
    uzz
    1.25
    yya
    1.24
    k
    1.24
    POSITIVE LOGITS
    確認
    1.53
    ώ
    1.52
    avait
    1.50
    机的
    1.48
     difficulté
    1.48
    금융
    1.47
    گیری
    1.46
     trajectory
    1.46
     difficulty
    1.44
    貥
    1.43
    Activations Density 0.000%

    No Known Activations