© 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. 34923
    Prev
    Next
    INDEX
    Explanations

    links and details

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

    The neuron fires on words that introduce or call out supplementary content or steps—e.g. “view,” “shown,” “read,” “prepared,” “more,” “fully,” etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    這些
    -1.00
    さまざま
    -0.84
     —
    -0.84
    𝑁
    -0.82
    さまざまな
    -0.82
     цього
    -0.82
     Proceed
    -0.82
    死去
    -0.82
     procede
    -0.82
    것은
    -0.81
    POSITIVE LOGITS
     below
    1.73
     here
    1.37
     see
    1.23
     details
    1.19
     article
    1.18
     https
    1.16
     см
    1.11
     examples
    1.11
    =")
    1.09
     HERE
    1.09
    Activations Density 0.159%

    No Known Activations