© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40366
    Prev
    Next
    INDEX
    Explanations

    proposals submissions

    np_acts-logits-general · gemini-2.5-flash-lite

    submit or upload

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     いく
    0.46
     सेगमेंट
    0.44
    Ⲓ
    0.42
    ନ
    0.42
     exercices
    0.40
     sporad
    0.40
    convers
    0.40
     важных
    0.40
    ⵏ
    0.40
    枻
    0.40
    POSITIVE LOGITS
     submitted
    0.68
     제출
    0.61
     submission
    0.61
    提交
    0.56
     submitting
    0.55
    必须
    0.54
     submit
    0.54
     Submitted
    0.48
     must
    0.48
     minimum
    0.46
    Activations Density 0.143%

    No Known Activations