© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112343
    Prev
    Next
    INDEX
    Explanations

    acronyms and specific terms

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

    proper nouns and brand names, particularly acronyms and capitalized terms.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is triggered by numeric values expressed with decimal points (i.e. floating-point numbers).

    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
    鸶
    -3.72
    䛗
    -3.53
    Ꭳ
    -3.34
    𞤢
    -3.31
    慙
    -3.20
     pérd
    -3.19
    ︕
    -3.03
    鯔
    -3.02
     INGREDIENTS
    -2.98
    
    -2.91
    POSITIVE LOGITS
    L
    3.11
     {
    2.98
     другими
    2.77
     Other
    2.52
     of
    2.50
     “
    2.48
     *
    2.47
     Because
    2.39
     With
    2.38
    <b>
    2.36
    Activations Density 0.021%

    No Known Activations