© 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. 179542
    Prev
    Next
    INDEX
    Explanations

    be responsible or held totally

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

    emergency, safety, or programming

    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
    手
    0.54
     procedure
    0.47
     오전
    0.47
     shortened
    0.47
     child
    0.46
    '
    0.46
    ’
    0.46
    ch
    0.44
     काम
    0.44
     southern
    0.44
    POSITIVE LOGITS
    ]^{+}$
    0.52
    たちの
    0.50
    တို့ကို
    0.50
     funkci
    0.48
    ๔
    0.47
     takich
    0.47
     Altos
    0.47
    들아
    0.46
     Öffentlichkeit
    0.46
     récit
    0.44
    Activations Density 0.001%

    No Known Activations