© 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. 183857
    Prev
    Next
    INDEX
    Explanations

    flesh nature

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

    new situations or tasks

    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
     Phenomenology
    0.49
     Europ
    0.45
     letech
    0.45
    льним
    0.45
     koz
    0.44
     Reason
    0.43
     Super
    0.43
     t
    0.43
     Nobel
    0.43
     fiz
    0.42
    POSITIVE LOGITS
    anship
    0.49
     escenario
    0.48
    ದಗ
    0.48
    ھا
    0.47
     envía
    0.45
    uestra
    0.45
     paisaje
    0.45
    願意
    0.45
    Creates
    0.45
    會
    0.44
    Activations Density 0.001%

    No Known Activations