© 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. 75248
    Prev
    Next
    INDEX
    Explanations

    first names, followed by surname

    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
     brisa
    -1.80
     turista
    -1.63
     traje
    -1.59
     morada
    -1.55
     their
    -1.54
     barco
    -1.54
     our
    -1.53
     maleta
    -1.52
    camisetas
    -1.50
     any
    -1.49
    POSITIVE LOGITS
    f
    1.39
    1.34
    ad
    1.31
    on
    1.31
    can
    1.30
    P
    1.30
    y
    1.29
    u
    1.27
    so
    1.26
    </b>
    1.25
    Activations Density 0.015%

    No Known Activations