© 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. 22-GEMMASCOPE-RES-131K
    7. 67136
    Prev
    Next
    INDEX
    Explanations

    He wrote, Tiny Gnomes, Fine art

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

    This neuron activates on UNIX filesystem path components, particularly the sequence “share/texmf-dist/scripts.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     jugadores
    -1.19
    Bq
    -1.05
    sibly
    -1.03
     mít
    -1.02
     janeiro
    -1.00
     quí
    -0.99
     résist
    -0.99
    ⇿
    -0.99
    ('/:
    -0.99
    𝐿
    -0.97
    POSITIVE LOGITS
     paio
    0.99
     these
    0.98
     Ślą
    0.95
     for
    0.93
     newest
    0.92
     where
    0.90
    4
    0.88
    5
    0.88
     there
    0.88
    Extrait
    0.88
    Activations Density 0.001%

    No Known Activations