© 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. 39195
    Prev
    Next
    INDEX
    Explanations

    start of HTML documentation

    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
     Spanyol
    -1.57
     katalog
    -1.52
    傒
    -1.50
     corrom
    -1.46
     berikan
    -1.38
     frança
    -1.38
     galeri
    -1.36
     musikal
    -1.35
     OGSÅ
    -1.34
     belas
    -1.34
    POSITIVE LOGITS
     with
    1.48
     just
    1.32
     now
    1.26
     nestled
    1.22
    just
    1.22
    ////////////////
    1.20
    节奏
    1.14
     on
    1.10
    𝒙
    1.09
     buena
    1.09
    Activations Density 0.015%

    No Known Activations