© 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. 116001
    Prev
    Next
    INDEX
    Explanations

    advertisement and customer demographics

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

    abuse, retail, dashboard, exposure

    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
    hashes
    0.46
     乗
    0.43
     设计
    0.42
     andre
    0.42
     fáb
    0.42
    ه‌ها
    0.42
     設計
    0.41
     そして
    0.40
    Ē
    0.40
     成
    0.40
    POSITIVE LOGITS
    те
    0.47
    ନ
    0.46
    데이트
    0.46
    যখন
    0.45
    when
    0.44
    ホテル
    0.44
    ;
    0.43
    ник
    0.42
     menace
    0.42
    wenn
    0.42
    Activations Density 0.000%

    No Known Activations