© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113585
    Prev
    Next
    INDEX
    Explanations

    word endings

    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
     its
    -1.95
    Its
    -1.55
     Its
    -1.52
     here
    -1.51
    ly
    -1.45
     how
    -1.45
     who
    -1.41
    its
    -1.41
     to
    -1.41
     there
    -1.37
    POSITIVE LOGITS
     and
    2.47
    rechter
    1.72
     včetně
    1.72
    datable
    1.70
     allerlei
    1.66
     olika
    1.66
     balkon
    1.63
    various
    1.55
     redak
    1.53
    følge
    1.51
    Activations Density 0.200%

    No Known Activations