© 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. 151352
    Prev
    Next
    INDEX
    Explanations

    subsidies, anyone, PHP, headed

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

    Processing, widely accessible, scalable

    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
    障害
    0.48
    鱉
    0.47
     WHEN
    0.45
     समांतर
    0.44
    際に
    0.44
     канторы
    0.43
    この
    0.43
     representando
    0.43
    豊富
    0.42
     跳转
    0.42
    POSITIVE LOGITS
    poetry
    0.50
    لى
    0.48
     või
    0.45
    jew
    0.44
     محک
    0.44
     k
    0.43
    又は
    0.43
     localhost
    0.42
     joked
    0.42
     няко
    0.42
    Activations Density 0.000%

    No Known Activations