© 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. 55348
    Prev
    Next
    INDEX
    Explanations

    higher altitudes, thousand miles

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

    refusal to provide dangerous information

    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
    셰
    0.51
    ฎ
    0.50
    ש
    0.48
    ዳል
    0.47
    嫋
    0.45
    énieur
    0.44
    േഷ്
    0.43
    ㅐ
    0.43
    ش
    0.43
    ಹ್
    0.42
    POSITIVE LOGITS
    meas
    0.48
    Rx
    0.47
    conference
    0.46
     welcomed
    0.45
     scooped
    0.44
    adoras
    0.44
     spp
    0.44
    😩
    0.44
    cookies
    0.44
     untuk
    0.44
    Activations Density 0.000%

    No Known Activations