© 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. 87414
    Prev
    Next
    INDEX
    Explanations

    death, denied, dangerous

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

    refusal or unwillingness

    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
    н
    0.49
    ভূত
    0.46
     régional
    0.45
     تضم
    0.45
    作
    0.45
    ন
    0.44
    न
    0.43
    وف
    0.42
     preferably
    0.42
    of
    0.42
    POSITIVE LOGITS
     básica
    0.47
     FAVOR
    0.47
     buyers
    0.45
    isma
    0.45
    ನೇ
    0.45
     Default
    0.45
    GISLATIVE
    0.44
     DEFAULT
    0.44
     ہاتھ
    0.44
     جميلة
    0.44
    Activations Density 0.001%

    No Known Activations