© 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. 34-GEMMASCOPE-RES-131K
    7. 82816
    Prev
    Next
    INDEX
    Explanations

    sequencing followed by analysis

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

    technical and scientific terminology, particularly in biological and computer science contexts.

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

    The neuron activates on numeric tokens, i.e. it finds numbers and quantitative 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_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
     खरीदा
    -0.82
     dispositivo
    -0.78
    spectrum
    -0.73
    wire
    -0.73
     mechanism
    -0.71
    farb
    -0.70
     EEG
    -0.69
    sendFile
    -0.69
     Николай
    -0.69
     Juventus
    -0.68
    POSITIVE LOGITS
     timelapse
    1.20
     microscope
    1.08
     movies
    1.05
     fluorescence
    1.01
     Microscope
    0.99
    Fiji
    0.91
     Bleach
    0.90
    Bleach
    0.90
     bleaching
    0.89
    bleach
    0.89
    Activations Density 0.018%

    No Known Activations