© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12636
    Prev
    Next
    INDEX
    Explanations

    heartbeat, beats, pounding

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    .”
    -1.66
     definitivo
    -1.59
    ceuticals
    -1.50
    婠
    -1.48
    zheng
    -1.45
    cantara
    -1.45
     négo
    -1.45
     visibilité
    -1.43
    ща
    -1.41
     PREVIOUS
    -1.41
    POSITIVE LOGITS
     different
    1.76
    '
    1.69
     heartbeat
    1.66
    {
    1.60
    ),
    1.59
     pounding
    1.55
    -
    1.53
    n
    1.44
    apatilla
    1.39
     Patrick
    1.38
    Activations Density 0.021%

    No Known Activations