© 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. 61089
    Prev
    Next
    INDEX
    Explanations

    population and epithelium

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

    references to human populations or demographic information.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects decimal numbers (floating-point numeric values) in the text.

    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
     vorigen
    -2.27
     Zeitraum
    -2.23
     Verlauf
    -2.09
     capucha
    -2.08
     classico
    -2.02
    之前
    -1.93
     cittadino
    -1.89
    姈
    -1.88
     selben
    -1.87
    It
    -1.85
    POSITIVE LOGITS
     of
    2.31
     is
    2.19
    뿍
    2.13
    </sup>
    2.11
     ''
    2.06
     by
    1.98
         
    1.91
    瀦
    1.89
    濑
    1.87
                    
    1.84
    Activations Density 0.000%

    No Known Activations