© 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. 104230
    Prev
    Next
    INDEX
    Explanations

    obtain or get services

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

    representing code or mathematical notation

    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
     balanced
    0.55
    Balanced
    0.53
     Balanced
    0.50
    \\
    0.50
    较高的
    0.48
     Conservative
    0.46
    F
    0.46
     maintaining
    0.46
     preserving
    0.46
    ↵↵↵
    0.46
    POSITIVE LOGITS
     skute
    0.49
     zaměst
    0.48
    говор
    0.47
     tady
    0.47
     入っ
    0.47
     quiso
    0.47
     paździer
    0.46
     পড়িল
    0.45
     sơn
    0.45
    পরিচিত
    0.44
    Activations Density 0.002%

    No Known Activations