© 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. 15759
    Prev
    Next
    INDEX
    Explanations

    reporting sources

    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
     Россия
    -0.89
     chamado
    -0.89
    remember
    -0.88
     außerdem
    -0.88
    久し
    -0.88
     nime
    -0.87
    licopter
    -0.86
    '},
    -0.86
    定価
    -0.86
    )),
    -0.85
    POSITIVE LOGITS
     according
    1.84
     said
    1.50
     says
    1.38
     spokesman
    1.32
     wrote
    1.16
     spokesperson
    1.15
    According
    1.14
     report
    1.11
    according
    1.02
     writes
    0.93
    Activations Density 0.055%

    No Known Activations