© 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. 80097
    Prev
    Next
    INDEX
    Explanations

    Executive and aspects

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

    used for malicious purposes

    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
    ↵
    0.54
    ی
    0.54
    لی
    0.49
    การ
    0.48
    ع
    0.48
    ژ
    0.48
    ี่
    0.47
    ופ
    0.47
    ี
    0.47
    지
    0.46
    POSITIVE LOGITS
     DQN
    0.52
    ற்றில்
    0.51
    ியல்
    0.50
     atraves
    0.46
     TUM
    0.46
     シャツ
    0.46
     OTHER
    0.45
    घाडी
    0.45
     egym
    0.45
    䉍
    0.45
    Activations Density 0.001%

    No Known Activations