© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90419
    Prev
    Next
    INDEX
    Explanations

    cerebellar cortex, nuclei, and functions

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

    terminology related to the cerebellum and cerebellar structures in neurological contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ଥ
    -0.79
     Ahh
    -0.77
    lenburg
    -0.75
     Broward
    -0.74
    linik
    -0.71
    👶
    -0.71
    ريق
    -0.71
     Restart
    -0.71
     Bengali
    -0.71
     Samos
    -0.69
    POSITIVE LOGITS
     cerebellar
    1.45
     cerebellum
    1.41
     Cere
    1.32
     vermis
    1.23
     Pur
    1.11
    cere
    1.01
     cere
    0.98
    ocere
    0.98
    Pur
    0.97
     cereal
    0.92
    Activations Density 0.082%

    No Known Activations