© 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. 231285
    Prev
    Next
    INDEX
    Explanations

    continues across or of

    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
    支持
    0.48
     সহযোগিতা
    0.48
    傚
    0.47
     대해
    0.47
    atsioon
    0.46
    urgical
    0.46
    鄙
    0.46
    Ꮑ
    0.44
     appendages
    0.44
    锈钢
    0.44
    POSITIVE LOGITS
     caz
    0.49
    を使
    0.46
     ボタン
    0.46
     cw
    0.46
     Watson
    0.46
     USO
    0.46
     CBD
    0.45
     顔
    0.45
    ラスト
    0.44
     エネルギー
    0.44
    Activations Density 0.000%

    No Known Activations