© 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. 9635
    Prev
    Next
    INDEX
    Explanations

    Linux and .NET projects

    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
     each
    -1.23
     from
    -1.12
     both
    -1.08
     without
    -1.05
     including
    -1.05
     that
    -1.05
    These
    -1.05
    To
    -1.03
    As
    -1.02
     as
    -1.02
    POSITIVE LOGITS
     linke
    1.13
     könig
    1.13
    
    1.13
    Kval
    1.05
     fotball
    1.03
    gaben
    1.02
    Stad
    1.01
    fondo
    1.01
    encre
    1.00
    chaleco
    0.99
    Activations Density 0.010%

    No Known Activations