© 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. 157072
    Prev
    Next
    INDEX
    Explanations

    prohibiting or special conditions

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

    SSH host key policy

    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
    辊
    0.52
     এবার
    0.50
     반드시
    0.50
    ится
    0.48
     पवार
    0.48
    uyền
    0.48
     مستقیم
    0.48
     수학
    0.47
    锜
    0.46
    ર્મ
    0.45
    POSITIVE LOGITS
    快樂
    0.49
     lament
    0.48
    WRITE
    0.47
     disagreeable
    0.47
     civilized
    0.45
     prohibiting
    0.45
    の良い
    0.45
     exhibited
    0.44
     fortuit
    0.44
    屠
    0.43
    Activations Density 0.001%

    No Known Activations