© 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. 95739
    Prev
    Next
    INDEX
    Explanations

    MATLAB programming

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

    This neuron specializes in detecting numeric constants (standalone numbers) 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_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
    ͆
    -1.11
    influenced
    -1.06
     mereka
    -1.05
     Influ
    -1.03
    قامة
    -1.02
    vital
    -1.02
    ͳ
    -1.02
     tilbage
    -1.00
     kisah
    -1.00
     bedien
    -1.00
    POSITIVE LOGITS
    MATLAB
    1.49
     MATLAB
    1.45
     Matlab
    1.20
     varargin
    1.20
     nargin
    1.15
     matlab
    1.11
    在这里
    1.11
    varargin
    1.08
    anno
    1.04
    ânea
    1.02
    Activations Density 0.055%

    No Known Activations