© 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. 65549
    Prev
    Next
    INDEX
    Explanations

    number ranges

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

    the presence of numeric tokens (digits or numerical measurements) 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
     significantly
    -1.09
     -
    -1.08
     neither
    -1.04
     another
    -0.95
     -"
    -0.92
    ...(
    -0.91
     promptly
    -0.90
    ありますか
    -0.89
    透过
    -0.87
     weiteren
    -0.86
    POSITIVE LOGITS
     depending
    1.69
    depending
    1.45
     Depending
    1.23
     dependiendo
    1.21
    不等
    1.20
    Depending
    1.20
     között
    1.16
    ٴ
    1.09
    viève
    1.04
    Karakteristik
    1.03
    Activations Density 0.071%

    No Known Activations