© 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. 90387
    Prev
    Next
    INDEX
    Explanations

    programming constructs

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

    The neuron fires on code identifier tokens—names of variables, classes, methods, etc.

    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
    -1.09
     giving
    -0.88
     all
    -0.85
     eds
    -0.85
     Like
    -0.84
     being
    -0.84
     as
    -0.82
    鈎
    -0.82
    ————————————————
    -0.80
    '}
    -0.79
    POSITIVE LOGITS
     Adicion
    1.09
    提到
    1.07
     accél
    1.05
     récol
    1.02
     tambien
    1.02
     Paramètres
    1.01
    demás
    1.01
    也都
    0.99
     précip
    0.98
     Ejemplo
    0.96
    Activations Density 0.011%

    No Known Activations