© 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. 22145
    Prev
    Next
    INDEX
    Explanations

    looked at

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

    The neuron lights up on content-bearing words (not on function words or punctuation), i.e. it detects lexically meaningful tokens such as verbs and nouns.

    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
     the
    -2.80
    鱨
    -2.73
    鶿
    -2.58
     a
    -2.34
    镲
    -2.33
    ܆
    -2.28
    嗵
    -2.27
    
    -2.27
     verschillende
    -2.23
     emballage
    -2.23
    POSITIVE LOGITS
     It
    2.45
     to
    2.38
     его
    2.27
     was
    2.13
     in
    2.09
     encontr
    1.97
     teniendo
    1.97
        
    1.97
         
    1.95
     get
    1.92
    Activations Density 0.120%

    No Known Activations