© 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. 184890
    Prev
    Next
    INDEX
    Explanations

    person, pregnancy, development, us, professional, subject, check, culture

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

    your task is to assist

    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
    ্বা
    0.47
    তরাং
    0.45
    ெல்லாம்
    0.45
    嘔
    0.45
    אס
    0.45
    ೆಂಟ್
    0.45
     我的
    0.45
    ϕ
    0.44
    ಾರ್ಟ
    0.44
    কিত
    0.43
    POSITIVE LOGITS
     nags
    0.52
     údaje
    0.52
     wollte
    0.52
     visitor
    0.51
     cinch
    0.49
     dese
    0.49
     parameter
    0.46
     erro
    0.46
     eram
    0.46
     mendorong
    0.45
    Activations Density 0.000%

    No Known Activations