© 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. 245189
    Prev
    Next
    INDEX
    Explanations

    specifying amount or duration

    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
     collabor
    0.52
     HAV
    0.51
     tiger
    0.50
     HA
    0.49
     defendant
    0.49
     banjir
    0.48
     tööt
    0.47
    麼
    0.46
     HH
    0.46
     et
    0.46
    POSITIVE LOGITS
    wonder
    0.55
     Ро
    0.55
    funny
    0.52
    reliant
    0.49
    opened
    0.48
    wedding
    0.48
    thinking
    0.48
    ledger
    0.47
     सोचा
    0.47
    Meth
    0.47
    Activations Density 0.000%

    No Known Activations