© 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. 577
    Prev
    Next
    INDEX
    Explanations

    charaterized

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

    code structure and explanations

    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
    מ
    0.42
    רו
    0.38
    ן
    0.38
    ש
    0.38
    АР
    0.37
    АН
    0.37
    בי
    0.37
     totalitarian
    0.37
    ל
    0.36
    ק
    0.36
    POSITIVE LOGITS
     fiori
    0.37
     Flower
    0.34
     Violet
    0.34
     ተጨማሪ
    0.34
     combo
    0.33
     femelle
    0.33
     Jdbc
    0.33
     same
    0.33
     beiden
    0.33
     Other
    0.32
    Activations Density 0.031%

    No Known Activations