© 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. 160663
    Prev
    Next
    INDEX
    Explanations

    automatic, sports, hand, reporter, length, were

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

    chooses or automatic

    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
    ació
    0.54
    señ
    0.50
    ௫
    0.48
    ród
    0.48
     ORD
    0.47
    dır
    0.46
    uję
    0.46
    ció
    0.45
    rfc
    0.45
     kilomètres
    0.45
    POSITIVE LOGITS
     自動
    0.49
     วิธี
    0.49
     거기
    0.45
    自動
    0.45
    、
    0.43
    RAIT
    0.43
     設計
    0.42
    簡易
    0.42
     इसके
    0.42
    的方法
    0.41
    Activations Density 0.000%

    No Known Activations