© 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. 64984
    Prev
    Next
    INDEX
    Explanations

    date, development, sizes, occur, known, exists

    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
     a
    -1.37
    !!!!!!!!
    -1.36
    !!!!!!!!!!!!!!!!
    -1.30
    !!!!!!
    -1.29
    !!!!!!!
    -1.20
     исключительно
    -1.20
     homicidio
    -1.17
     problemet
    -1.16
     içerisinde
    -1.16
     geschreven
    -1.15
    POSITIVE LOGITS
    Procedimento
    1.30
    全都
    1.17
     面包
    1.13
    颼
    1.11
    Prova
    1.10
    参见
    1.09
    人气
    1.09
     gradual
    1.08
    Ār
    1.06
    怎么回事
    1.05
    Activations Density 0.166%

    No Known Activations