© 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. 103672
    Prev
    Next
    INDEX
    Explanations

    U.S. News and World Report form

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

    This neuron detects words or abbreviations containing internal punctuation (e.g. hyphens, semicolons, or embedded periods).

    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
    訁
    -1.88
     ส์
    -1.86
    idlertid
    -1.75
     Âge
    -1.72
     colorear
    -1.71
    
    -1.70
    ⸱
    -1.70
     transmite
    -1.70
     distanciation
    -1.69
     delightful
    -1.68
    POSITIVE LOGITS
    E
    2.53
    e
    2.53
    er
    2.39
    S
    2.23
    ‘
    2.16
    C
    2.14
    O
    2.14
    A
    2.11
    V
    2.08
    </h1>
    2.06
    Activations Density 0.004%

    No Known Activations