© 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. 73271
    Prev
    Next
    INDEX
    Explanations

    keratinocytes and related tissues

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

    This neuron detects the word "keratin" and related cellular/biological terminology.

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

    The neuron specializes in detecting occurrences of the word “keratin” (and its derivatives such as “keratinocytes”).

    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
    我们
    -2.27
     главный
    -2.22
    
    -2.20
     ſou
    -2.14
     dekoratif
    -2.09
    
    -2.06
     frescas
    -2.02
    uminense
    -1.98
    っていて
    -1.95
     調整
    -1.95
    POSITIVE LOGITS
     наиболее
    2.00
    接着
    1.90
    lässlich
    1.87
    
    1.83
     беже
    1.78
    ated
    1.73
     Nuestros
    1.72
    我只
    1.71
     $_{
    1.70
     tubuh
    1.69
    Activations Density 0.015%

    No Known Activations