© 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. 10-GEMMASCOPE-RES-131K
    7. 8216
    Prev
    Next
    INDEX
    Explanations

    And

    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_10/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
     
    -1.85
    L
    -1.61
     работают
    -1.50
    P
    -1.45
    However
    -1.44
     A
    -1.41
    飾り
    -1.38
    Things
    -1.36
    ka
    -1.35
    U
    -1.34
    POSITIVE LOGITS
    ЦИИ
    1.70
    welli
    1.61
    饜
    1.51
     adesso
    1.50
    杳
    1.49
     speelt
    1.47
    ordinaire
    1.46
     contoh
    1.41
    ênis
    1.39
     parteci
    1.38
    Activations Density 0.001%

    No Known Activations