© 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. 194124
    Prev
    Next
    INDEX
    Explanations

    date format

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

    parts of common phrases

    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
    ת
    0.54
    ي
    0.54
    د
    0.52
    ل
    0.47
    <b>
    0.46
    و
    0.46
     cauldron
    0.46
     veggies
    0.46
     turmeric
    0.45
     Tested
    0.45
    POSITIVE LOGITS
    codewords
    0.54
    𝓻
    0.53
    reate
    0.53
     여기서
    0.48
    populate
    0.48
     форма
    0.48
     үш
    0.47
    make
    0.46
     типу
    0.46
     ভে
    0.46
    Activations Density 0.000%

    No Known Activations