© 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. 36213
    Prev
    Next
    INDEX
    Explanations

    contrast or exception

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

    explaining refusal

    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
     क्रा
    0.40
    ὼ
    0.39
    一样
    0.39
    ี่ยม
    0.38
     belki
    0.37
    رق
    0.37
     хими
    0.37
    衩
    0.37
    যদিও
    0.36
    لكتر
    0.36
    POSITIVE LOGITS
     shouldn
    0.56
     exaggeration
    0.52
     excessive
    0.50
     exagger
    0.50
    格外
    0.49
     Excessive
    0.48
     excuse
    0.48
     excessively
    0.47
     exager
    0.46
     egreg
    0.46
    Activations Density 0.083%

    No Known Activations