© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101432
    Prev
    Next
    INDEX
    Explanations

    realy, ately, pears

    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_10/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
     there
    -2.86
     at
    -2.69
    1
    -2.44
    In
    -2.41
     this
    -2.27
     these
    -2.27
    After
    -2.25
    There
    -2.20
     both
    -2.19
     of
    -2.16
    POSITIVE LOGITS
     😁
    2.38
    😊
    2.34
    
    2.33
    
    2.25
     😊
    2.23
     ſal
    2.22
     petites
    2.17
     ........
    2.13
     speciale
    2.11
    咴
    2.11
    Activations Density 0.079%

    No Known Activations