© 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. 81250
    Prev
    Next
    INDEX
    Explanations

    countries and places

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

    surfers alike

    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
    converting
    0.50
    inducing
    0.46
     आरा
    0.46
     incompatibility
    0.46
    on
    0.45
    overlapping
    0.45
     म
    0.45
     infest
    0.45
     locales
    0.45
     participantes
    0.44
    POSITIVE LOGITS
     ځ
    0.48
    CodeAttribute
    0.46
    တ်
    0.46
    рма
    0.45
    ගත්
    0.44
    班
    0.44
     strop
    0.43
    Simulator
    0.43
    гъ
    0.42
     christ
    0.42
    Activations Density 0.000%

    No Known Activations