© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75430
    Prev
    Next
    INDEX
    Explanations

    plays and dramas

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

    This neuron selectively fires on uppercase or numeric tokens—e.g. headings, titles, acronyms, and year‐numbers—essentially detecting document metadata elements.

    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
    ULOS
    -0.82
     תק
    -0.82
     scam
    -0.79
    ')
    -0.75
     Commun
    -0.74
    canestro
    -0.73
     RECIP
    -0.73
     Vap
    -0.72
    ',
    -0.72
    BarButtonItem
    -0.71
    POSITIVE LOGITS
     politiques
    0.88
    ėk
    0.76
    ējās
    0.72
     Marlowe
    0.71
    urses
    0.70
    strtolower
    0.69
    anonymous
    0.69
    Ql
    0.69
     tragedy
    0.69
     anonymous
    0.68
    Activations Density 0.024%

    No Known Activations