© 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. 144809
    Prev
    Next
    INDEX
    Explanations

    Carnegie Hall, linoleic acid, Arnoux

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

    Carnitine, Heinz, Heinrich

    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
    il
    0.45
    Piano
    0.44
    巖
    0.41
     ವಿಧಾನಸ
    0.40
    [*
    0.40
    phone
    0.40
    ej
    0.39
    初
    0.39
    千
    0.39
    gress
    0.39
    POSITIVE LOGITS
     starved
    0.47
     Enrico
    0.43
     Germanic
    0.42
    ylobacter
    0.42
     "}
    0.42
     vitamina
    0.41
     வினை
    0.41
     Campania
    0.41
     Германии
    0.41
     African
    0.41
    Activations Density 0.127%

    No Known Activations