© 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. 31754
    Prev
    Next
    INDEX
    Explanations

    alternatives, or descriptions that contrast

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

    electricity and its measurement

    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
     PubMed
    0.52
     Hause
    0.48
    items
    0.47
    İK
    0.47
    builder
    0.46
     Kluwer
    0.46
     Deduction
    0.46
    ↵
    0.46
     HPLC
    0.45
     FRA
    0.45
    POSITIVE LOGITS
     aterriz
    0.56
     aprovechar
    0.53
     cuy
    0.50
     brindar
    0.49
    戦争
    0.49
    যেন
    0.49
     alarg
    0.49
    бавить
    0.48
     averiguar
    0.48
     estabelecer
    0.47
    Activations Density 0.000%

    No Known Activations