© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14591
    Prev
    Next
    INDEX
    Explanations

    selection of measurement instruments

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

    The neuron fires on uncommon, domain‐specific jargon and technical terms (e.g. specialized nouns and acronyms).

    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
    ⚕
    -0.98
    Ciri
    -0.90
    heit
    -0.85
     Dennoch
    -0.84
    має
    -0.83
     tropicales
    -0.82
    例の
    -0.80
     மற்றும்
    -0.79
     metr
    -0.79
    Reserve
    -0.79
    POSITIVE LOGITS
     selection
    2.59
     choice
    2.19
     chosen
    2.02
     choices
    1.91
     Selection
    1.85
     selected
    1.68
    selection
    1.62
     선택
    1.61
    Selection
    1.58
    的选择
    1.55
    Activations Density 0.159%

    No Known Activations