© 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. 38338
    Prev
    Next
    INDEX
    Explanations

    code compilation validation

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

    The neuron fires on content-bearing words (not function words)—i.e. domain-specific nouns and verbs—rather than on common stopwords.

    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
    парат
    -0.85
     температуры
    -0.84
    alumnos
    -0.82
     softened
    -0.80
    imágenes
    -0.79
    вест
    -0.79
    プロン
    -0.77
     estekak
    -0.77
     certiorari
    -0.77
    brot
    -0.76
    POSITIVE LOGITS
     validation
    1.16
     validate
    1.12
    validation
    1.08
     approval
    1.07
     approve
    1.04
    validate
    1.04
     approved
    1.02
    validates
    1.02
    Validate
    1.01
     validates
    1.00
    Activations Density 0.225%

    No Known Activations