© 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. 129337
    Prev
    Next
    INDEX
    Explanations

    prior to

    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
     vertrou
    -0.82
    Сейчас
    -0.77
    Today
    -0.75
     znajdują
    -0.72
    oldest
    -0.71
     innova
    -0.71
     peme
    -0.71
    ارنة
    -0.71
    MITTED
    -0.70
     pesce
    -0.70
    POSITIVE LOGITS
     again
    1.45
     anew
    1.12
    again
    1.03
    rett
    0.88
     novamente
    0.87
    ٥
    0.85
     finally
    0.82
    Bliss
    0.80
     gewor
    0.79
     nuevamente
    0.79
    Activations Density 0.162%

    No Known Activations