© 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. 145396
    Prev
    Next
    INDEX
    Explanations

    Wolf, Bob, Sunset, interim

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

    explaining terms and definitions

    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
    س
    0.61
    ت
    0.50
     Washington
    0.49
     Bacon
    0.47
    т
    0.46
    স
    0.45
    ين
    0.45
     Fabrication
    0.45
    E
    0.44
     Kral
    0.44
    POSITIVE LOGITS
    ajan
    0.54
    kec
    0.50
    TTLE
    0.45
     multicolored
    0.45
    daftar
    0.45
     acetaldehyde
    0.45
    kowicz
    0.44
     별
    0.44
     ajj
    0.44
    bokeh
    0.44
    Activations Density 0.000%

    No Known Activations