© 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. 228725
    Prev
    Next
    INDEX
    Explanations

    individual number

    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
     sebenarnya
    0.58
     courthouse
    0.57
     veranda
    0.56
     Sony
    0.54
     Bethel
    0.54
     父
    0.54
     Bosch
    0.53
     konstru
    0.52
     Westinghouse
    0.52
     Verwaltungs
    0.52
    POSITIVE LOGITS
    ranu
    0.45
     $>$
    0.44
    usian
    0.44
    bs
    0.43
    >?
    0.42
    ση
    0.42
    gaia
    0.42
    wn
    0.41
    umu
    0.41
    bai
    0.41
    Activations Density 0.000%

    No Known Activations