© 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. 25636
    Prev
    Next
    INDEX
    Explanations

    documentary film

    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
     for
    -1.37
     as
    -1.32
     can
    -1.27
     has
    -1.26
    .
    -1.26
     at
    -1.22
    !
    -1.14
    ,
    -1.11
     are
    -1.11
     S
    -1.11
    POSITIVE LOGITS
     documentary
    1.77
    dokument
    1.44
    αιν
    1.41
     documentaries
    1.41
     interro
    1.40
     filmed
    1.38
     footage
    1.38
    ені
    1.32
     dokumenti
    1.31
     документа
    1.30
    Activations Density 0.070%

    No Known Activations