© 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. 84631
    Prev
    Next
    INDEX
    Explanations

    great/gran

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

    This neuron responds to words that convey large magnitude or intensity (e.g. “great,” “gran,” “grande,” “número”).

    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
    䊐
    -2.45
    ícias
    -2.44
    𐬹
    -2.33
    苤
    -2.20
    岽
    -2.19
     câbles
    -2.16
    圌
    -2.16
     dando
    -2.13
     tt
    -2.13
    
    -2.11
    POSITIVE LOGITS
    t
    3.16
    u
    2.72
     burgeoning
    2.27
     Almost
    2.25
     longstanding
    2.22
     Shortly
    2.20
     multifaceted
    2.20
     Surprisingly
    2.17
     Following
    2.16
    先日
    2.16
    Activations Density 0.002%

    No Known Activations