© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38512
    Prev
    Next
    INDEX
    Explanations

    path and include statements

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

    The neuron fires on numeric tokens (isolated digits or numbers) in source 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_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
     so
    -1.20
     weird
    -1.07
     by
    -1.07
     inapropiados
    -1.02
     in
    -0.99
     strangely
    -0.97
     does
    -0.95
     fantaisie
    -0.92
     strange
    -0.91
    Spel
    -0.90
    POSITIVE LOGITS
    /
    1.31
     .........
    1.20
    -------
    1.15
    readFileSync
    1.11
    และ
    1.08
    ----------
    1.08
    TestBed
    1.07
    ............
    1.07
     ............
    1.05
    ...............
    1.05
    Activations Density 0.058%

    No Known Activations