© 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. 49393
    Prev
    Next
    INDEX
    Explanations

    license and copyright notices

    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
     in
    -1.36
     on
    -1.19
     for
    -1.19
     despite
    -1.17
     had
    -1.11
     less
    -1.08
     at
    -1.07
     Despite
    -1.06
     with
    -1.05
     new
    -1.02
    POSITIVE LOGITS
    //
    1.48
     vijf
    1.18
    Modifica
    1.16
     MODERN
    1.13
    廡
    1.11
     spécialement
    1.09
     spektak
    1.08
     –
    1.07
     chacune
    1.07
     températures
    1.06
    Activations Density 0.132%

    No Known Activations