© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8660
    Prev
    Next
    INDEX
    Explanations

    stroke

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

    words related to "stroke" in both medical and physical movement 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_10/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
    {
    -2.63
    t
    -2.55
    ve
    -2.55
    E
    -2.33
    d
    -2.31
    /
    -2.25
    ce
    -2.19
    la
    -2.17
    しっかり
    -2.13
    ING
    -2.09
    POSITIVE LOGITS
    meteries
    2.66
     Vereinbarung
    2.52
    tedì
    2.39
     stroking
    2.38
     Strukt
    2.36
     Για
    2.34
     ένα
    2.30
    唿
    2.30
     Problemen
    2.28
     bekämp
    2.28
    Activations Density 0.010%

    No Known Activations