© 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. 69190
    Prev
    Next
    INDEX
    Explanations

    Championship season or defend

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

    Hugging Face Spaces demos

    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
     Pas
    0.63
     Puro
    0.57
    ח
    0.54
    δα
    0.54
     des
    0.52
    Pas
    0.52
    ahlen
    0.52
    t
    0.52
    س
    0.50
     اس
    0.48
    POSITIVE LOGITS
    ଘ
    0.49
    契
    0.48
    startsWith
    0.46
    した
    0.46
    েব
    0.45
    姏
    0.44
     proximity
    0.44
    parentNode
    0.43
     ROBERT
    0.43
     흥
    0.43
    Activations Density 0.001%

    No Known Activations