© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203791
    Prev
    Next
    INDEX
    Explanations

    explanation and procedures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ز
    0.50
    ahanam
    0.48
    cotton
    0.47
    meria
    0.46
    ute
    0.45
    chlorate
    0.45
    roz
    0.45
    endim
    0.44
    ru
    0.44
     j
    0.44
    POSITIVE LOGITS
     宝宝
    0.48
     Utils
    0.46
     দুর্ঘটনার
    0.45
     fichier
    0.44
     breakaway
    0.44
     convexe
    0.44
     arrondi
    0.44
    일을
    0.43
    叧
    0.43
     partenaires
    0.43
    Activations Density 0.002%

    No Known Activations