© 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. 26848
    Prev
    Next
    INDEX
    Explanations

    code returns

    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
     realização
    -1.14
     العديد
    -1.08
     различ
    -1.07
     assinatura
    -1.06
     execução
    -1.05
    similar
    -1.05
     içeris
    -1.05
     Setiap
    -1.05
     duração
    -1.04
    !!!!!!!
    -1.01
    POSITIVE LOGITS
     of
    1.52
     with
    1.39
     from
    1.37
     (
    1.26
     and
    1.05
     вси
    1.05
     when
    1.04
     or
    1.02
     until
    0.98
     if
    0.98
    Activations Density 0.001%

    No Known Activations