© 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. 22-GEMMASCOPE-RES-131K
    7. 34441
    Prev
    Next
    INDEX
    Explanations

    XML attributes and properties

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

    The neuron reliably flags chunks of source‐code or markup (e.g. HTML/XML tags and code‐style snippets).

    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
     hanya
    -1.13
    ấc
    -1.06
     that
    -1.05
     Einzelnen
    -1.01
     diperhatikan
    -0.98
     bahagia
    -0.97
     dikirim
    -0.97
     Besitzer
    -0.95
    nze
    -0.94
    యు
    -0.94
    POSITIVE LOGITS
    发明
    1.01
     tokenize
    0.93
    Reconnect
    0.92
    hadores
    0.90
    Primal
    0.90
    rierung
    0.88
     despond
    0.88
    ₱
    0.87
    Bry
    0.87
     culoare
    0.86
    Activations Density 0.000%

    No Known Activations