© 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. 102610
    Prev
    Next
    INDEX
    Explanations

    largest manmade

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

    Streamlit app development

    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
    🎨
    0.47
     provoz
    0.47
     cotisation
    0.46
     coss
    0.46
    드로
    0.45
     الداخلية
    0.44
     бя
    0.44
    ✮
    0.43
     webhook
    0.43
    decoration
    0.42
    POSITIVE LOGITS
    的研究
    0.48
     overestimated
    0.46
     Berkeley
    0.46
     Americans
    0.45
    Berkeley
    0.42
     Baylor
    0.42
     overestimate
    0.41
     America
    0.39
     Bernoulli
    0.39
     Eber
    0.39
    Activations Density 0.000%

    No Known Activations