© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109074
    Prev
    Next
    INDEX
    Explanations

    license terms (MERCHANTABILITY) or Italian links

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

    The neuron fires on numeric tokens—years, version numbers, bare digits, etc.—wherever numbers appear 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_34/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
     under
    -0.90
    룻
    -0.73
     SONY
    -0.72
    under
    -0.71
    enerbahçe
    -0.70
    
    -0.68
    말
    -0.68
    Yvonne
    -0.68
     bbq
    -0.68
    Disposal
    -0.67
    POSITIVE LOGITS
    getActiveSheet
    0.69
     географи
    0.67
    ectors
    0.65
     аль
    0.65
    ANC
    0.64
     dobre
    0.63
     Duggan
    0.62
     Secure
    0.61
     personal
    0.61
    mined
    0.60
    Activations Density 0.051%

    No Known Activations