© 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. 88179
    Prev
    Next
    INDEX
    Explanations

    business or services

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

    refusal to continue provided text/prompt

    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
    bul
    0.48
    檛
    0.46
    dere
    0.46
    gaxModule
    0.44
    centes
    0.44
     సై
    0.44
     உறுதி
    0.43
     discontinuities
    0.42
    neck
    0.42
    ForItem
    0.42
    POSITIVE LOGITS
    점
    0.54
     हाईकोर्ट
    0.48
    Джо
    0.47
    스타
    0.47
    сур
    0.46
     sínt
    0.46
     sphing
    0.46
    史
    0.44
    ور
    0.44
     STP
    0.44
    Activations Density 0.001%

    No Known Activations