© 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. 25410
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     QWidget
    -1.07
    וּ
    -1.02
     mín
    -1.01
     TAMBÉM
    -1.00
     aros
    -1.00
     álbum
    -0.99
    ﺃ
    -0.98
     antena
    -0.95
    gemini
    -0.94
    ּוֹ
    -0.94
    POSITIVE LOGITS
    )}-\
    1.06
     различные
    1.02
     verschiedene
    1.00
     MANY
    0.98
    ილ
    0.96
     håller
    0.96
    ne
    0.95
     hochwer
    0.94
    本章完
    0.93
    oczes
    0.93
    Activations Density 0.001%

    No Known Activations