© 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. 196577
    Prev
    Next
    INDEX
    Explanations

    everyone or you supporting

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

    complaint or CC

    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
     ✅
    0.49
    ниць
    0.48
     tote
    0.48
     Whole
    0.48
     تث
    0.48
    వ్వు
    0.47
     ఉత్పత్తి
    0.46
     tová
    0.46
    ඟ
    0.46
     നമ്മ
    0.44
    POSITIVE LOGITS
     lectura
    0.52
    t
    0.48
    l
    0.46
    re
    0.44
    asked
    0.44
     cuadr
    0.43
    leu
    0.43
    ষ্টিত
    0.43
    ggen
    0.42
    le
    0.42
    Activations Density 0.001%

    No Known Activations