© 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. 71575
    Prev
    Next
    INDEX
    Explanations

    incorrect, incomplete, expired

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

    missed payment or insignificant

    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
     retelling
    0.52
    曉
    0.49
     buyout
    0.47
     reprint
    0.46
    ኪያ
    0.46
    షణ
    0.44
     evergreen
    0.44
     recount
    0.43
    ляем
    0.43
    ᒡ
    0.43
    POSITIVE LOGITS
    ന്ത്രാ
    0.50
    anska
    0.49
    ani
    0.48
     بالنسبة
    0.47
    yi
    0.46
    Burg
    0.44
     بهذه
    0.43
    iect
    0.43
    தாக
    0.43
     انگلیسی
    0.43
    Activations Density 0.001%

    No Known Activations