© 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. 10-GEMMASCOPE-RES-131K
    7. 8892
    Prev
    Next
    INDEX
    Explanations

    variable declarations

    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
     they
    -1.46
    with
    -1.41
    尤其是
    -1.38
     kerana
    -1.33
    now
    -1.31
    this
    -1.31
    including
    -1.27
     möjlighet
    -1.26
    特别是
    -1.25
     skydd
    -1.24
    POSITIVE LOGITS
     aktual
    1.23
     confirmer
    1.15
     插图
    1.13
    絰
    1.12
     autorisation
    1.11
    綃
    1.11
    ೞ
    1.10
    ILLING
    1.07
     ſie
    1.06
     LUZ
    1.05
    Activations Density 0.019%

    No Known Activations