© 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. 38880
    Prev
    Next
    INDEX
    Explanations

    collective intake, word spreads

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

    explains or demonstrates concepts

    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
    ----------------
    0.45
    star
    0.44
    everything
    0.44
     everything
    0.42
     vitamin
    0.41
     metabolic
    0.41
    ☆
    0.41
    ！！！
    0.40
     mysteriously
    0.40
    <em>
    0.39
    POSITIVE LOGITS
    恳
    0.44
    uestros
    0.44
    檐
    0.43
    ጠቀም
    0.42
    وزيع
    0.42
    ków
    0.41
     Stowe
    0.41
    совой
    0.41
    圩
    0.41
     steeple
    0.41
    Activations Density 0.000%

    No Known Activations