© 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. 8001
    Prev
    Next
    INDEX
    Explanations

    units of measure and locations

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

    function condition variable representation

    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
    性和
    0.49
     unmittelbar
    0.47
     नती
    0.45
    clusively
    0.45
    4
    0.45
    ؟.
    0.44
    7
    0.43
    administered
    0.43
    )}.
    0.43
    raising
    0.42
    POSITIVE LOGITS
     tenemos
    0.63
     hebben
    0.58
     temos
    0.56
     ہے
    0.53
     abbiamo
    0.52
     máme
    0.52
    非常的
    0.52
     comes
    0.51
     heeft
    0.51
     oldukça
    0.51
    Activations Density 0.064%

    No Known Activations