© 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. 240896
    Prev
    Next
    INDEX
    Explanations

    pro-social, productive way of life

    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
    قة
    0.53
    ，
    0.48
     tipos
    0.48
     qilish
    0.48
     Katie
    0.47
     quinoa
    0.47
    सबुक
    0.46
     effett
    0.45
     应
    0.45
     silica
    0.45
    POSITIVE LOGITS
    렜
    0.49
    Rendering
    0.49
     neglected
    0.48
     inclinations
    0.48
    Hyderabad
    0.48
    меня
    0.48
    pesar
    0.47
     incompatibility
    0.47
    toArray
    0.47
     నట
    0.46
    Activations Density 0.003%

    No Known Activations