© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144088
    Prev
    Next
    INDEX
    Explanations

    dough, feathered, never grows, sanity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     watery
    0.47
    就
    0.46
     easiest
    0.45
     MARKET
    0.45
     easier
    0.44
    OD
    0.44
     fewer
    0.42
    EN
    0.42
    Easy
    0.42
     primers
    0.42
    POSITIVE LOGITS
    <unused666>
    0.50
    ♉
    0.49
     nonché
    0.49
     аў
    0.49
    وين
    0.48
    revalidator
    0.48
    uine
    0.46
     Расійскай
    0.46
     نوفمبر
    0.46
     maan
    0.45
    Activations Density 0.004%

    No Known Activations