© 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. 82687
    Prev
    Next
    INDEX
    Explanations

    Laravel support and permissions

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

    This neuron activates on code tokens that are library or namespace identifiers (e.g. module/package names in include paths or namespaces).

    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
    چھ
    -0.83
    Sierra
    -0.78
    diğimiz
    -0.77
     Mark
    -0.74
     Ligue
    -0.73
     última
    -0.72
    适
    -0.72
    aconda
    -0.72
     föres
    -0.71
     ideje
    -0.71
    POSITIVE LOGITS
     str
    0.88
     individuales
    0.80
     Tennyson
    0.79
    fac
    0.77
    str
    0.77
     vacacionales
    0.76
     фаса
    0.75
     Fac
    0.74
    oires
    0.74
    illi
    0.73
    Activations Density 0.005%

    No Known Activations