© 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. 89207
    Prev
    Next
    INDEX
    Explanations

    numbers and phone

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

    describing scale or intensity

    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
     outages
    0.54
    ەکانی
    0.52
    ścic
    0.52
     wynika
    0.51
    ęcia
    0.49
    𝚕
    0.48
    cció
    0.48
    isjon
    0.48
     ръ
    0.48
     东
    0.47
    POSITIVE LOGITS
     calorimeter
    0.49
     glacier
    0.45
     jasper
    0.45
     hummingbird
    0.45
     caldo
    0.42
     tapped
    0.41
    fclose
    0.41
    த்துவ
    0.41
     profundidad
    0.40
    atmosphère
    0.39
    Activations Density 0.001%

    No Known Activations