© 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. 22-GEMMASCOPE-RES-131K
    7. 66928
    Prev
    Next
    INDEX
    Explanations

    rinsing, washing, flushing liquids

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

    washing or rinsing processes in technical or procedural 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_22/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
    {
    -2.02
    [
    -1.62
    n
    -1.43
    _
    -1.43
    <
    -1.41
    <b>
    -1.40
     a
    -1.38
    \
    -1.38
     there
    -1.34
    =
    -1.34
    POSITIVE LOGITS
     TAMBIÉN
    1.41
    Suara
    1.39
    🕗
    1.38
     Europeo
    1.33
    woordig
    1.32
    …」
    1.32
     tir
    1.31
    ﮨ
    1.31
    rillation
    1.30
    Tons
    1.30
    Activations Density 0.007%

    No Known Activations