© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40444
    Prev
    Next
    INDEX
    Explanations

    WebVim configuration

    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_10/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
     for
    -1.41
     âges
    -1.34
    groet
    -1.32
     $^{\
    -1.31
     médec
    -1.27
     ноги
    -1.23
     грамо
    -1.20
    .''
    -1.16
     générations
    -1.16
     doar
    -1.15
    POSITIVE LOGITS
     there
    1.77
     історі
    1.42
    aéroport
    1.34
     religiosas
    1.32
    orgung
    1.31
     начинает
    1.29
     müsse
    1.28
     зовні
    1.28
     cristianismo
    1.27
     Jeśli
    1.25
    Activations Density 0.014%

    No Known Activations