© 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. 34-GEMMASCOPE-RES-131K
    7. 31268
    Prev
    Next
    INDEX
    Explanations

    on the right track

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

    The main thing this neuron does is detect numeric tokens (numbers and numerical 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
     follow
    -0.93
    follow
    -0.92
     garantía
    -0.85
    habilitar
    -0.80
    nä
    -0.79
    Follow
    -0.79
    Conn
    -0.77
    
    -0.77
    closing
    -0.75
    Licz
    -0.75
    POSITIVE LOGITS
     path
    2.28
     track
    2.20
     tracks
    1.59
    path
    1.44
     Track
    1.43
    track
    1.42
    軌道
    1.41
     Path
    1.34
     TRACK
    1.33
     paths
    1.31
    Activations Density 0.021%

    No Known Activations