© 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. 135389
    Prev
    Next
    INDEX
    Explanations

    refusal to

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

    by explainers

    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
    胼
    0.50
    夸
    0.50
    อา
    0.49
    꼐
    0.49
    拁
    0.49
    randomIndex
    0.47
    Ყ
    0.47
    玛
    0.46
    áo
    0.45
    夺
    0.45
    POSITIVE LOGITS
     regulators
    0.44
    Hrs
    0.42
    t
    0.41
     cleanliness
    0.40
     Covered
    0.40
    ify
    0.40
     sicherlich
    0.39
     raising
    0.39
     retaining
    0.39
    drift
    0.38
    Activations Density 0.000%

    No Known Activations