© 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. 38367
    Prev
    Next
    INDEX
    Explanations

    past events and actions

    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
     sonre
    -1.00
    textnormal
    -0.91
    所说的
    -0.85
    contenedor
    -0.85
     segundo
    -0.85
    そりゃ
    -0.82
     what
    -0.81
    こんばん
    -0.81
    了的
    -0.80
    Ufficio
    -0.80
    POSITIVE LOGITS
     also
    1.22
     these
    1.14
     hierfür
    1.13
     solch
    1.09
    这些
    1.00
     inoltre
    1.00
     storici
    0.99
    ęku
    0.98
     также
    0.98
     такие
    0.94
    Activations Density 0.034%

    No Known Activations