© 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. 58544
    Prev
    Next
    INDEX
    Explanations

    web page sections

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

    run from the command line

    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
     iaitu
    0.63
    which
    0.56
    यदि
    0.55
    of
    0.52
    dengan
    0.52
    ※
    0.51
    หรือ
    0.51
    ש
    0.50
    became
    0.50
    un
    0.49
    POSITIVE LOGITS
     çizg
    0.49
     don
    0.46
     cowork
    0.44
     gotta
    0.44
     neuest
    0.43
     fórm
    0.43
     whatnot
    0.42
     carbure
    0.42
     bont
    0.41
     αρχ
    0.41
    Activations Density 0.017%

    No Known Activations