© 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. 23500
    Prev
    Next
    INDEX
    Explanations

    fit and match

    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_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
    しかったです
    -0.79
    Inhalation
    -0.77
     Ters
    -0.76
    bigoplus
    -0.73
     Salut
    -0.73
    IndexPath
    -0.72
     制
    -0.72
     Dijk
    -0.72
     zil
    -0.70
    ร์
    -0.69
    POSITIVE LOGITS
     fit
    3.59
     fits
    2.61
    fit
    2.61
     match
    2.56
     matches
    2.22
     Fit
    2.17
    Fit
    2.13
    match
    2.06
    fits
    1.98
     Fits
    1.86
    Activations Density 0.034%

    No Known Activations