© 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. 165693
    Prev
    Next
    INDEX
    Explanations

    certifications and submissions

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

    tiny explanations

    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
     burl
    0.54
    aundice
    0.50
     пар
    0.47
    я
    0.47
     ঠাকুর
    0.47
    affiche
    0.46
    ibur
    0.46
    t
    0.45
     protruding
    0.45
    стье
    0.45
    POSITIVE LOGITS
    सामान्यीकृत
    0.46
    Time
    0.46
     produk
    0.44
     sende
    0.43
    Seed
    0.42
    Property
    0.42
    ندو
    0.42
     felhasznál
    0.42
     kultur
    0.42
     onların
    0.41
    Activations Density 0.001%

    No Known Activations