© 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. 22-GEMMASCOPE-RES-131K
    7. 93122
    Prev
    Next
    INDEX
    Explanations

    keywords for code declarations

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

    The neuron activates on numeric literals (integer constants) 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_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
    andır
    -1.27
     Ál
    -1.18
     alqu
    -1.16
    lijken
    -1.16
     comité
    -1.14
     that
    -1.12
     turun
    -1.12
    عف
    -1.11
     Président
    -1.10
     esperan
    -1.10
    POSITIVE LOGITS
    o
    1.46
     also
    1.39
     bestehenden
    1.30
     Hinsicht
    1.27
    og
    1.19
     vielmehr
    1.18
    O
    1.16
    ch
    1.14
    r
    1.14
     späteren
    1.12
    Activations Density 0.061%

    No Known Activations