© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99388
    Prev
    Next
    INDEX
    Explanations

    width and depth

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

    The main thing this neuron does is identify numerical measurement values (dimensions, quantities, or specifications).

    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
     westfalen
    -1.47
     interfaz
    -1.45
     limba
    -1.43
     vicente
    -1.41
    HIS
    -1.38
     juc
    -1.38
     cadastro
    -1.37
     misterioso
    -1.35
    橚
    -1.34
     geda
    -1.30
    POSITIVE LOGITS
     If
    1.63
    周泽
    1.47
     any
    1.44
     And
    1.43
     dieser
    1.40
     this
    1.38
     когда
    1.38
    主要的
    1.37
     This
    1.36
     может
    1.36
    Activations Density 0.057%

    No Known Activations