© 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. 10-GEMMASCOPE-RES-131K
    7. 13513
    Prev
    Next
    INDEX
    Explanations

    float, double, bool

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

    This neuron flags occurrences of the “double” floating‐point type (casts, parsing calls, etc.) 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_10/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
     suced
    -1.88
     hatten
    -1.73
     hadden
    -1.65
    他不
    -1.52
     tuvo
    -1.46
     lesiones
    -1.45
     donde
    -1.45
    ❘
    -1.45
     expresa
    -1.44
    ௧
    -1.42
    POSITIVE LOGITS
    2
    2.09
     illustratie
    1.61
    雠
    1.55
     emitir
    1.55
     เป็น
    1.50
     JAKARTA
    1.48
    𐐪
    1.45
     ersche
    1.45
     Allgemeinen
    1.42
    縺
    1.41
    Activations Density 0.013%

    No Known Activations