© 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. 168674
    Prev
    Next
    INDEX
    Explanations

    foreign words and numbers

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

    references previous rows, incoming transport, or explaining meaning

    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
    i
    0.48
    自从
    0.48
    lo
    0.47
     Indonesia
    0.46
    bon
    0.45
    ke
    0.45
    ber
    0.45
    ц
    0.44
    子
    0.44
    伊
    0.44
    POSITIVE LOGITS
     acidity
    0.55
     wobble
    0.52
     fragility
    0.50
     magari
    0.48
     travaille
    0.47
     väldigt
    0.47
     eigenlijk
    0.46
     كث
    0.46
     porosity
    0.46
     інте
    0.46
    Activations Density 0.001%

    No Known Activations