© 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. 34-GEMMASCOPE-RES-131K
    7. 48588
    Prev
    Next
    INDEX
    Explanations

    in favour of

    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
    ्यान
    -0.98
    変わらない
    -0.93
     metales
    -0.92
    踮
    -0.90
     nhung
    -0.89
     colocación
    -0.89
     manicura
    -0.88
    変わらず
    -0.88
     みた
    -0.87
    レーター
    -0.86
    POSITIVE LOGITS
     favor
    3.14
     favour
    3.00
     preferring
    2.11
     favoring
    2.11
    favor
    1.97
    fav
    1.90
     favore
    1.89
     replaced
    1.88
     to
    1.80
     Favor
    1.78
    Activations Density 0.058%

    No Known Activations