© 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. 16087
    Prev
    Next
    INDEX
    Explanations

    college team rankings

    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
     which
    -1.24
    了不少
    -1.05
    aurus
    -1.05
     regata
    -1.05
    ’
    -1.04
    coder
    -1.04
    焢
    -1.03
    instein
    -1.02
    şiv
    -1.01
    čilo
    -1.00
    POSITIVE LOGITS
     бъ
    0.92
    Dimethyl
    0.89
     представителей
    0.88
     Klasse
    0.88
    ptăm
    0.88
     UN
    0.86
    Према
    0.86
    estatus
    0.84
     Daher
    0.84
    Dea
    0.84
    Activations Density 0.006%

    No Known Activations