© 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. 126120
    Prev
    Next
    INDEX
    Explanations

    promote, coordinator, committee

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

    I cannot refuse

    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
    ิ
    0.50
     Geschwindigkeit
    0.46
     வீட்டில்
    0.45
    нуть
    0.43
     listrik
    0.43
     כאשר
    0.42
    ző
    0.42
    ylvania
    0.41
    របស់
    0.41
    ,]
    0.41
    POSITIVE LOGITS
     iniciativa
    0.64
     coordinator
    0.57
     promoter
    0.54
     committee
    0.54
     اللجنة
    0.54
     anonym
    0.53
     Ombudsman
    0.53
     an
    0.53
     deleg
    0.53
     promote
    0.52
    Activations Density 0.001%

    No Known Activations