© 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. 22-GEMMASCOPE-RES-131K
    7. 38984
    Prev
    Next
    INDEX
    Explanations

    Q:

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

    The neuron detects function or method declarations (i.e. lines defining methods).

    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
     Startseite
    -1.14
     effective
    -0.93
     bought
    -0.92
     Sprecher
    -0.91
     була
    -0.89
     będę
    -0.86
     Streit
    -0.86
     organisatie
    -0.85
     houses
    -0.84
    spaceBetween
    -0.84
    POSITIVE LOGITS
    BOTH
    1.20
    тату
    1.07
    віду
    1.07
    both
    1.02
    Both
    0.99
     thermos
    0.95
     neop
    0.93
     BOTH
    0.92
     petición
    0.91
    richtig
    0.90
    Activations Density 0.000%

    No Known Activations