© 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. 224392
    Prev
    Next
    INDEX
    Explanations

    "so too", "only right", "computer ."

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

    technical details

    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
     hab
    0.52
     penultimate
    0.50
     longitude
    0.46
     habits
    0.45
     habitats
    0.44
     raster
    0.44
     pen
    0.43
     五
    0.43
     spaces
    0.43
    hab
    0.42
    POSITIVE LOGITS
    鍱
    0.50
    芡
    0.46
    Britt
    0.46
    ляться
    0.46
    essayer
    0.46
    Leather
    0.44
    কার্য
    0.44
    Dans
    0.43
    İstanbul
    0.43
    Innov
    0.43
    Activations Density 0.003%

    No Known Activations