© 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. 246319
    Prev
    Next
    INDEX
    Explanations

    functional programming

    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
    大
    0.55
     tratamiento
    0.50
     treatment
    0.47
    mated
    0.47
    olded
    0.46
    olina
    0.46
     plaisir
    0.46
    reated
    0.45
    ø
    0.44
     guilty
    0.44
    POSITIVE LOGITS
    Func
    0.48
    iť
    0.45
     паў
    0.45
    നം
    0.44
    Algo
    0.44
    TestMethod
    0.44
    வும்
    0.44
    Scheduler
    0.43
    assertThat
    0.43
    getMax
    0.43
    Activations Density 0.001%

    No Known Activations