© 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. 57582
    Prev
    Next
    INDEX
    Explanations

    Android UI item XML

    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
    -0.95
    ghouse
    -0.86
    публи
    -0.84
     első
    -0.84
    flüs
    -0.83
    haviours
    -0.81
    *",
    -0.81
     Институ
    -0.79
     observar
    -0.79
    supreme
    -0.79
    POSITIVE LOGITS
     چنین
    0.85
    켭
    0.85
     sams
    0.83
    UMAR
    0.83
     कह
    0.82
     tenda
    0.81
     Harlequin
    0.81
     autre
    0.80
    溪
    0.80
     Wallflower
    0.78
    Activations Density 0.001%

    No Known Activations