© 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. 168356
    Prev
    Next
    INDEX
    Explanations

    our/a followed by noun

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

    Portugal, Nginx, mRNA

    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
     Eternity
    0.52
    پ
    0.46
    녹
    0.45
    esquerdo
    0.45
    ሎች
    0.44
    дино
    0.44
    不必
    0.44
    ancji
    0.44
    萺
    0.44
    ujących
    0.43
    POSITIVE LOGITS
    debt
    0.54
     debt
    0.53
     সাল
    0.50
    skill
    0.47
    tax
    0.47
    weather
    0.46
    astar
    0.46
     batting
    0.45
     workings
    0.45
     chapter
    0.45
    Activations Density 0.000%

    No Known Activations