© 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. 107191
    Prev
    Next
    INDEX
    Explanations

    menu items and specials

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

    The neuron detects capitalized code identifiers or proper‐noun–style tokens (e.g. class and variable names beginning with an uppercase letter).

    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
    wishlist
    -0.79
     rudimentary
    -0.78
    chaft
    -0.78
     culinary
    -0.76
    itate
    -0.75
     Culinary
    -0.75
    レクション
    -0.75
     contracting
    -0.75
    Dining
    -0.74
    joystick
    -0.74
    POSITIVE LOGITS
     drinks
    1.18
     menu
    1.13
     drink
    1.08
     complementos
    1.05
     extras
    1.00
     popularity
    0.99
     item
    0.98
     popular
    0.96
     Drinks
    0.96
    addons
    0.94
    Activations Density 0.008%

    No Known Activations