© 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. 179172
    Prev
    Next
    INDEX
    Explanations

    international monitoring, store terms

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

    capacity, also, find, control, traceability, person

    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
     Leica
    0.51
     verlassen
    0.50
     Years
    0.49
    ilah
    0.48
     comical
    0.48
     Lover
    0.47
     wondrous
    0.46
    Ꮠ
    0.46
     Newsom
    0.46
     thigh
    0.46
    POSITIVE LOGITS
     ато
    0.46
     caracteres
    0.46
     caractères
    0.44
    提及
    0.44
    screwdriver
    0.43
     patrones
    0.43
    defaultValue
    0.43
    PIRE
    0.42
    *****",
    0.42
     incentiv
    0.42
    Activations Density 0.001%

    No Known Activations