© 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. 41317
    Prev
    Next
    INDEX
    Explanations

    bombings by, made by

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

    logistics and transformations

    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
    лу
    0.48
    фо
    0.48
     камера
    0.48
     மிகப்
    0.47
     токси
    0.47
    轟
    0.46
     хра
    0.46
     запа
    0.46
    мию
    0.46
    э
    0.45
    POSITIVE LOGITS
     Jeddah
    0.53
     transfers
    0.52
     Indian
    0.52
     designations
    0.52
     sponsorship
    0.50
     INDIAN
    0.50
     applicability
    0.50
     Japanese
    0.50
     Saudi
    0.50
     alternates
    0.48
    Activations Density 0.000%

    No Known Activations