© 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. 10-GEMMASCOPE-RES-131K
    7. 71213
    Prev
    Next
    INDEX
    Explanations

    able to

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

    The neuron detects words that express ability, capacity, or eligibility (e.g., “able,” “capable,” “eligible”).

    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
     a
    -1.69
     who
    -1.66
    O
    -1.53
    OS
    -1.51
    ”、“
    -1.50
    The
    -1.50
    」、「
    -1.48
     are
    -1.47
    ”
    -1.45
    必须
    -1.43
    POSITIVE LOGITS
     sonhos
    1.67
     Carcinoma
    1.66
     knihy
    1.66
    嘥
    1.63
    stär
    1.61
    favorite
    1.55
    嬲
    1.52
     UIImage
    1.52
     článek
    1.50
     unui
    1.47
    Activations Density 0.019%

    No Known Activations