© 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. 36068
    Prev
    Next
    INDEX
    Explanations

    title followed by key/value data

    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
    {
    -3.03
    '
    -2.77
    ."
    -2.61
    ),
    -2.38
     що
    -2.34
     for
    -2.25
    ülete
    -2.23
    k
    -2.17
     erhielten
    -2.03
    U
    -2.03
    POSITIVE LOGITS
    齪
    3.09
    .”
    2.78
    ⚋
    2.72
     bliss
    2.63
    
    2.58
    𓋼
    2.55
    üşonlu
    2.52
    But
    2.47
    أما
    2.45
    鐒
    2.42
    Activations Density 0.030%

    No Known Activations