© 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. 34-GEMMASCOPE-RES-131K
    7. 47455
    Prev
    Next
    INDEX
    Explanations

    sentence start punctuation

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

    This neuron detects paragraph, section, or footnote reference numbers in legal‐style documents.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     like
    -1.13
     αὐ
    -1.06
     ἐκ
    -1.02
     cabrio
    -0.97
     gilet
    -0.93
     τὸν
    -0.91
     chaises
    -0.90
     validations
    -0.90
     diamant
    -0.88
     susceptibles
    -0.88
    POSITIVE LOGITS
     it
    2.34
     vivere
    1.26
     in
    1.14
     결
    1.10
     bearing
    1.10
     counsel
    1.10
     borsa
    1.07
    에서는
    1.06
     the
    1.04
     în
    1.03
    Activations Density 0.008%

    No Known Activations