© 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. 35639
    Prev
    Next
    INDEX
    Explanations

    refusing harmful requests about groups

    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
    。『
    0.45
     lorsque
    0.44
    甥
    0.43
     Wohnung
    0.41
    というと
    0.40
    codile
    0.40
     ดังนั้น
    0.40
     GATE
    0.39
    weite
    0.39
     เมื่อ
    0.39
    POSITIVE LOGITS
     nostrum
    0.54
     puns
    0.52
     akust
    0.51
     pellets
    0.49
     любых
    0.48
     остальных
    0.47
    д
    0.47
     aliqua
    0.46
     infusions
    0.45
     gutters
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.