© 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. 102730
    Prev
    Next
    INDEX
    Explanations

    under one

    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
    被他
    -1.18
     Rptr
    -1.16
     stället
    -1.16
     praktische
    -1.16
     anklicken
    -1.16
     historischen
    -1.12
     perdida
    -1.11
     to
    -1.11
     retirado
    -1.11
     things
    -1.10
    POSITIVE LOGITS
     the
    1.38
     вони
    1.30
    Sometimes
    1.29
    洗面
    1.28
    Honestly
    1.23
    Sumber
    1.22
     redor
    1.20
    𝘾
    1.19
    की
    1.19
     Bought
    1.17
    Activations Density 0.520%

    No Known Activations