© 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. 69274
    Prev
    Next
    INDEX
    Explanations

    Q:

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

    This neuron identifies technical or domain-specific jargon words often found in code comments and documentation.

    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
    tyg
    -1.24
     their
    -1.24
    krok
    -1.19
    tinggi
    -1.16
     there
    -1.15
     have
    -1.15
    tinta
    -1.13
    braz
    -1.10
     maravilhoso
    -1.09
    kadang
    -1.09
    POSITIVE LOGITS
    though
    1.30
    などが
    1.20
     getApplication
    1.16
    vation
    1.13
    ano
    1.13
    agonal
    1.09
    tablissement
    1.09
    ash
    1.09
     '.';
    1.09
     expre
    1.05
    Activations Density 0.000%

    No Known Activations