© 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. 27909
    Prev
    Next
    INDEX
    Explanations

    program entry points

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

    The neuron fires strongly on code‐block openings—specifically on the identifier that names a class or method and the following “{” that begins its definition.

    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
    breviations
    -1.16
    tribune
    -1.08
    ॥
    -1.06
     milhões
    -1.00
    OW
    -0.97
     To
    -0.95
    డా
    -0.94
    ෞ
    -0.94
    Ehrungen
    -0.94
     zwischen
    -0.93
    POSITIVE LOGITS
    CCIÓN
    1.13
    sistence
    1.00
    Lalu
    0.99
     fernández
    0.98
     駅前
    0.98
     couldn
    0.97
     didn
    0.95
     akumulator
    0.94
     contrôler
    0.94
     włosów
    0.94
    Activations Density 0.004%

    No Known Activations