© 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. 201956
    Prev
    Next
    INDEX
    Explanations

    previous month

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

    safe word

    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
     اعزائي
    0.47
     Honours
    0.45
     qualitative
    0.44
     quantitative
    0.43
    క్కువ
    0.42
    豫
    0.42
     Faculté
    0.41
     comprender
    0.40
    anov
    0.40
    realistic
    0.40
    POSITIVE LOGITS
     rollback
    0.49
     workaround
    0.49
    ↩
    0.45
    ปิด
    0.44
     isValid
    0.44
     файла
    0.43
    ंगामा
    0.42
     打开
    0.42
     getattr
    0.42
     redirect
    0.41
    Activations Density 0.001%

    No Known Activations