© 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. 67923
    Prev
    Next
    INDEX
    Explanations

    import paths and modules

    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
     by
    -1.61
     because
    -1.59
     has
    -1.54
     even
    -1.51
     also
    -1.45
     is
    -1.34
     it
    -1.30
     when
    -1.29
     if
    -1.27
     just
    -1.25
    POSITIVE LOGITS
    respectively
    1.73
     respectivement
    1.47
     célè
    1.36
    commonly
    1.36
    
    1.32
     visites
    1.30
    為に
    1.27
    wonderful
    1.26
     noten
    1.26
    beautiful
    1.26
    Activations Density 0.010%

    No Known Activations