© 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. 52293
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    groups or collections of items or ideas

    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
    ittää
    0.47
     tangle
    0.45
    ofy
    0.44
    slotBox
    0.43
     propel
    0.43
     セット
    0.43
     l
    0.42
     系列
    0.42
     ఎక్కువగా
    0.42
    evre
    0.41
    POSITIVE LOGITS
    recovery
    0.49
     ritorno
    0.48
    lardır
    0.48
     odgovor
    0.48
    Recovery
    0.47
    a
    0.47
    ા
    0.46
    苜
    0.46
    answers
    0.46
    Congressional
    0.46
    Activations Density 0.000%

    No Known Activations