© 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. 22-GEMMASCOPE-RES-131K
    7. 72895
    Prev
    Next
    INDEX
    Explanations

    a or an followed by a word

    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
     its
    -2.63
     itself
    -2.09
     is
    -1.87
     has
    -1.79
     was
    -1.63
    它
    -1.61
     one
    -1.52
     does
    -1.50
     it
    -1.41
     wasn
    -1.39
    POSITIVE LOGITS
     themselves
    2.98
     are
    2.59
    themselves
    2.39
     they
    1.73
     aren
    1.72
     eivät
    1.72
     których
    1.70
     έχουν
    1.70
    THEY
    1.63
     zostały
    1.61
    Activations Density 0.080%

    No Known Activations