© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8342
    Prev
    Next
    INDEX
    Explanations

    borrowing money or streaming content

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

    The neuron detects imperative or action‐oriented words in step‐by‐step “how-to” or instructional contexts (e.g. borrow, buy, check, stream).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     politica
    -1.41
    PASO
    -1.34
    Jawaban
    -1.32
    Ꮆ
    -1.32
    tigheter
    -1.31
    ኋ
    -1.31
     ajuta
    -1.27
     luminos
    -1.26
    Режи
    -1.26
     industria
    -1.25
    POSITIVE LOGITS
     a
    1.52
     then
    1.46
     from
    1.43
     is
    1.33
    '
    1.32
    1
    1.24
     '
    1.23
     in
    1.23
     how
    1.21
    \
    1.18
    Activations Density 0.057%

    No Known Activations