© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79683
    Prev
    Next
    INDEX
    Explanations

    code structure and config

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

    The neuron activates on programming declarations or metadata keywords (e.g. setup calls, package headers, and annotations like @Directive or @Component).

    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
    之后
    -1.49
    embang
    -1.32
     apabila
    -1.29
    一些
    -1.26
    ۔
    -1.24
    iaomi
    -1.23
    UREAU
    -1.20
     melalui
    -1.20
    ization
    -1.19
    crania
    -1.19
    POSITIVE LOGITS
     they
    1.39
    ’
    1.39
    更何况
    1.34
    doras
    1.33
     enseñ
    1.32
    何况
    1.30
     девочек
    1.30
    ↵
    1.28
     flourished
    1.28
     Witnesses
    1.27
    Activations Density 0.000%

    No Known Activations