© 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. 10-GEMMASCOPE-RES-131K
    7. 14000
    Prev
    Next
    INDEX
    Explanations

    pairing devices

    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
     of
    -2.45
     with
    -1.88
     нашей
    -1.55
    6
    -1.52
     unserer
    -1.49
    ければ
    -1.48
     naudoti
    -1.45
     necessárias
    -1.44
     его
    -1.41
    不宜
    -1.41
    POSITIVE LOGITS
    說道
    1.47
    intéress
    1.43
    ing
    1.43
     sandero
    1.42
     fara
    1.40
     inimigo
    1.40
     ..............
    1.39
    硨
    1.38
    няют
    1.38
     hardly
    1.38
    Activations Density 0.003%

    No Known Activations