© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14481
    Prev
    Next
    INDEX
    Explanations

    specific entities and attributions

    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
    dienne
    -1.08
     quando
    -0.94
     кно
    -0.93
    signable
    -0.92
    guarding
    -0.90
    zied
    -0.89
     ม
    -0.88
     Kontak
    -0.85
     ciclismo
    -0.84
     onAnimation
    -0.84
    POSITIVE LOGITS
     įva
    1.10
     in
    1.00
     dortmund
    0.94
    érat
    0.94
    ΕΙ
    0.93
     tidligere
    0.93
     galima
    0.90
    czech
    0.90
     않습니다
    0.90
    現実
    0.88
    Activations Density 0.003%

    No Known Activations