© 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. 65841
    Prev
    Next
    INDEX
    Explanations

    python method calls

    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
     tengo
    -1.20
     Introducción
    -1.15
     konfer
    -1.13
    nocześnie
    -1.12
     Disponible
    -1.11
     gobiernos
    -1.10
    Ḍ
    -1.10
     comedia
    -1.09
     disponible
    -1.09
     ceremonia
    -1.09
    POSITIVE LOGITS
     and
    1.77
     or
    1.66
     what
    1.52
     with
    1.32
     an
    1.29
     one
    1.27
     make
    1.22
     that
    1.19
     on
    1.17
     from
    1.16
    Activations Density 0.005%

    No Known Activations