© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25943
    Prev
    Next
    INDEX
    Explanations

    instantiate ViewController

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

    This neuron fires on programming code identifiers, in particular method or function names and related API calls.

    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
    LÄ
    -1.45
    DÉ
    -1.34
     bambou
    -1.29
    〤
    -1.24
     suporta
    -1.24
     permanece
    -1.22
     作り方
    -1.22
    Kör
    -1.21
    SALUD
    -1.21
     všechny
    -1.21
    POSITIVE LOGITS
    S
    1.62
    T
    1.61
    M
    1.48
    R
    1.45
    G
    1.44
    ,
    1.41
    He
    1.38
    It
    1.38
    A
    1.35
    P
    1.31
    Activations Density 0.018%

    No Known Activations