© 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. 10-GEMMASCOPE-RES-131K
    7. 13810
    Prev
    Next
    INDEX
    Explanations

    backgroundColor, headphones, backpack

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

    This neuron detects programming identifiers—especially CamelCase class, method, or property names in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    er
    -4.19
     This
    -3.98
     You
    -3.69
     当
    -3.44
    en
    -3.36
     Would
    -3.20
     selben
    -3.06
    (
    -3.06
     When
    -2.86
     Might
    -2.83
    POSITIVE LOGITS
     parachoque
    4.00
    垕
    3.36
     стоковые
    3.03
    蚡
    3.02
     oock
    2.92
    却不
    2.83
    獁
    2.81
    楡
    2.80
     vnnd
    2.78
     広場
    2.78
    Activations Density 0.004%

    No Known Activations