© 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. 33793
    Prev
    Next
    INDEX
    Explanations

    specific nouns following descriptions

    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
     of
    -1.27
     The
    -1.22
     both
    -1.20
     many
    -1.17
     most
    -1.16
     first
    -1.16
     First
    -1.13
     well
    -1.11
     only
    -1.11
     more
    -1.11
    POSITIVE LOGITS
     plafon
    1.38
    Variante
    1.36
     carburant
    1.36
    Lain
    1.22
    Technologie
    1.15
     consommate
    1.14
    Muh
    1.14
    晌
    1.13
    Netto
    1.13
    Kamera
    1.13
    Activations Density 0.371%

    No Known Activations