© 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. 26134
    Prev
    Next
    INDEX
    Explanations

    according to attributed names

    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
    кладки
    -0.97
    Fiesta
    -0.93
    Rozm
    -0.91
     поэтому
    -0.84
    Buona
    -0.84
     révélé
    -0.84
    gherita
    -0.84
    okia
    -0.81
    чта
    -0.81
     gỗ
    -0.81
    POSITIVE LOGITS
     they
    1.32
     representatives
    1.31
     their
    1.15
     representative
    1.15
     team
    1.13
     family
    1.13
     group
    1.13
     wó
    1.09
     spokesperson
    1.04
     edy
    1.02
    Activations Density 0.034%

    No Known Activations