© 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. 14538
    Prev
    Next
    INDEX
    Explanations

    declarations and code snippets

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

    The neuron activates on numeric literal tokens (decimal or hexadecimal constants) in 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_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
     reseña
    -1.09
    Zubereitung
    -1.07
     compétences
    -1.06
     escalier
    -1.05
    ៃ
    -1.02
     induk
    -1.02
    椟
    -1.02
    kew
    -1.02
     biblia
    -1.01
    loggen
    -1.01
    POSITIVE LOGITS
     many
    1.30
     K
    1.23
     Many
    1.20
     M
    1.15
     S
    1.15
     by
    1.14
     You
    1.14
     L
    1.12
     D
    1.11
     H
    1.10
    Activations Density 0.001%

    No Known Activations