© 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. 107121
    Prev
    Next
    INDEX
    Explanations

    routes, path, questions

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

    personal info screening

    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
     cél
    0.50
    杵
    0.50
     booms
    0.48
    旭
    0.48
     hoogte
    0.48
    東
    0.48
    設定
    0.48
    最強
    0.48
     setters
    0.47
    市值
    0.46
    POSITIVE LOGITS
    PersonalInfo
    0.43
     }}$.
    0.43
     Плавание
    0.43
     carelessly
    0.42
    ScreenBinding
    0.41
     ผ้า
    0.41
     ();
    0.41
    izabeth
    0.40
     TNumber
    0.40
    ูป
    0.39
    Activations Density 0.000%

    No Known Activations