© 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. 68039
    Prev
    Next
    INDEX
    Explanations

    url transformations

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

    The neuron strongly activates on numeric tokens (digits, numbers, and numeric sequences).

    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
    lerinden
    -0.89
    σταση
    -0.88
     berarti
    -0.85
    + 
    -0.84
    ſi
    -0.82
    fycat
    -0.82
    ufac
    -0.81
     createdBy
    -0.81
    غان
    -0.81
    alanx
    -0.81
    POSITIVE LOGITS
     Duits
    0.98
     Projektu
    0.94
    唷
    0.90
     эффективность
    0.85
    ‌شده
    0.83
    Nonetheless
    0.82
     intolerant
    0.81
    INFO
    0.80
    Nevertheless
    0.79
     muchísimo
    0.79
    Activations Density 0.065%

    No Known Activations