© 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. 40666
    Prev
    Next
    INDEX
    Explanations

    then followed by question or explanation

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

    The neuron flags tokens that mark ordered steps or list structure (e.g. numerals and sequence words like “First,” “Then,” 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_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
    ↵
    -2.16
    »,
    -1.55
    になる
    -1.50
     KEEP
    -1.49
    ;,
    -1.46
     "*",
    -1.38
     "",
    -1.38
     elegant
    -1.36
    “,
    -1.35
    "},
    -1.32
    POSITIVE LOGITS
     what
    1.55
     cannot
    1.49
     July
    1.46
     does
    1.46
     February
    1.45
     supremely
    1.41
     went
    1.41
     oddly
    1.41
     steadily
    1.41
     strangely
    1.40
    Activations Density 0.013%

    No Known Activations