© 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. 113393
    Prev
    Next
    INDEX
    Explanations

    saleexpressesarea

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

    sun exposure, features, additions

    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
    Histoire
    0.55
    Anglo
    0.47
    Botan
    0.47
     «
    0.46
    Singer
    0.46
    Placed
    0.46
    Jog
    0.45
    👸
    0.45
    Repost
    0.44
    ঈ
    0.44
    POSITIVE LOGITS
     tive
    0.52
     pomocí
    0.48
     ಮೂಲಕ
    0.46
     naudoj
    0.44
     tions
    0.44
     tion
    0.43
     vidhan
    0.43
     wykon
    0.42
     används
    0.42
     gov
    0.42
    Activations Density 0.001%

    No Known Activations