© 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. 103871
    Prev
    Next
    INDEX
    Explanations

    a 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_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
     you
    -1.65
     that
    -1.57
     through
    -1.49
     but
    -1.49
     our
    -1.40
     nieco
    -1.37
     former
    -1.37
     and
    -1.36
     things
    -1.32
     godziny
    -1.32
    POSITIVE LOGITS
     tė
    1.76
     asmen
    1.49
     laiko
    1.48
    Their
    1.48
    媵
    1.46
    </h4>
    1.44
    jetas
    1.40
    am
    1.40
     їх
    1.38
    Tableau
    1.38
    Activations Density 0.041%

    No Known Activations