© 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. 45312
    Prev
    Next
    INDEX
    Explanations

    refusing harmful requests and questions

    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
    тери
    0.52
    :-
    0.50
    ことが多い
    0.48
     tất
    0.47
    藤
    0.47
    ^{*}}\
    0.46
    íticos
    0.46
    老
    0.45
    使い
    0.45
    小学校
    0.44
    POSITIVE LOGITS
     wiederum
    0.52
     effectu
    0.43
    Produ
    0.43
     ہمارا
    0.43
    Loaded
    0.43
    Conformance
    0.42
    Refresh
    0.42
    Behaviour
    0.42
    Performing
    0.41
     behaviour
    0.41
    Activations Density 0.000%

    No Known Activations