© 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. 42965
    Prev
    Next
    INDEX
    Explanations

    exclamations

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

    The neuron activates on exclamation marks and similarly punctuated tokens indicating excitement or emphasis.

    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
    酹
    -1.70
    
    -1.66
     Balkon
    -1.52
    colgante
    -1.52
    ěr
    -1.51
    鹸
    -1.51
     upro
    -1.50
    نگار
    -1.48
    Weg
    -1.46
    震惊
    -1.45
    POSITIVE LOGITS
     to
    2.30
    也
    1.90
     The
    1.69
    時に
    1.59
    他の
    1.58
    the
    1.55
    These
    1.55
    顼
    1.53
    What
    1.52
    verläs
    1.52
    Activations Density 0.030%

    No Known Activations