© 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. 65932
    Prev
    Next
    INDEX
    Explanations

    setting properties or tags

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

    The neuron flags programming property or attribute names (e.g., Name, id, position, orientation) in code or markup.

    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
    AutoModerator
    -0.96
     their
    -0.96
     they
    -0.95
    ．．．
    -0.94
     to
    -0.91
     Hinsicht
    -0.88
    琊
    -0.88
     into
    -0.88
     อาหาร
    -0.87
    他們
    -0.87
    POSITIVE LOGITS
     tornillos
    1.13
     می‌کند
    1.07
    )}{\
    1.05
     nhung
    1.01
    aunque
    0.99
     teléfonos
    0.97
    zyła
    0.97
    ̋
    0.96
     necessidade
    0.95
     refuer
    0.95
    Activations Density 0.000%

    No Known Activations