© 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. 34-GEMMASCOPE-RES-131K
    7. 1541
    Prev
    Next
    INDEX
    Explanations

    years and events

    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_34/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
     vuonna
    -1.40
     nieuwe
    -1.31
     recientes
    -1.27
     ২০১
    -1.27
     depuis
    -1.22
     afgelopen
    -1.21
    すっ
    -1.20
     anunció
    -1.19
     presentó
    -1.19
     jaren
    -1.16
    POSITIVE LOGITS
     when
    1.77
     edition
    1.45
     which
    1.44
     what
    1.37
     with
    1.29
     where
    1.24
     still
    1.19
     iteration
    1.16
     after
    1.16
     that
    1.16
    Activations Density 0.116%

    No Known Activations