© 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-16K
    7. 11853
    Prev
    Next
    INDEX
    Explanations

    dots followed by word

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

    declining harmful requests

    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_16k_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
    은
    0.89
    は
    0.79
    2
    0.74
     všech
    0.73
    can
    0.71
     have
    0.68
    kan
    0.67
    miş
    0.66
    8
    0.66
    has
    0.64
    POSITIVE LOGITS
    д
    0.69
    м
    0.62
    ம்
    0.60
    ం
    0.56
    ன்
    0.54
     facil
    0.54
    naires
    0.54
    ్వ
    0.54
    чи
    0.52
     নদীর
    0.52
    Activations Density 0.005%

    No Known Activations