© 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. 117718
    Prev
    Next
    INDEX
    Explanations

    Italian language snippets

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

    The neuron fires on code “names” and identifiers—things like class or namespace names, function names, tag/attribute identifiers, and other programmer‐style tokens.

    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
    Consigli
    -1.23
    Scopri
    -1.20
    Caratter
    -1.05
    ඒ
    -1.03
    Saluti
    -1.02
    Quali
    -1.02
     thở
    -1.02
    LEGGI
    -0.98
     artful
    -0.98
     prodigal
    -0.98
    POSITIVE LOGITS
     dè
    1.12
     nè
    1.07
    
    1.06
     è
    1.05
     ù
    1.02
     vong
    1.01
    čnega
    0.99
    čnih
    0.98
     biel
    0.97
     พ
    0.97
    Activations Density 0.006%

    No Known Activations