© 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. 25473
    Prev
    Next
    INDEX
    Explanations

    names, authors, writers

    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
     bluza
    -1.18
     概要
    -1.13
     虾
    -1.10
     verschillende
    -1.09
     prachtige
    -1.07
    ších
    -1.05
    lamiento
    -1.05
     metrów
    -1.02
     angenehm
    -1.01
    Ꮖ
    -1.00
    POSITIVE LOGITS
    *}$
    1.20
    它们
    1.20
     (
    1.13
    它
    1.11
    gido
    1.08
    报记者
    1.08
    Così
    1.06
     –
    1.06
     -
    1.05
    Especially
    1.03
    Activations Density 0.012%

    No Known Activations