© 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. 22-GEMMASCOPE-RES-131K
    7. 104755
    Prev
    Next
    INDEX
    Explanations

    services, availability, convenience

    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_22/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
     GenerationType
    -0.82
    gorithm
    -0.81
     Antilles
    -0.80
    𝑄
    -0.79
    notNull
    -0.77
    ディア
    -0.76
    ธรรม
    -0.76
    delete
    -0.76
    óticas
    -0.75
    arcas
    -0.75
    POSITIVE LOGITS
     convenient
    1.63
     convenience
    1.43
    方便
    1.35
     удобно
    1.26
    Convenient
    1.20
     saves
    1.16
     conveniently
    1.09
    convenient
    1.08
    Convenience
    1.06
     सुवि
    1.05
    Activations Density 0.074%

    No Known Activations