© 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. 22170
    Prev
    Next
    INDEX
    Explanations

    warnings and safety information

    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
     can
    -1.55
     will
    -1.41
    {
    -1.27
     sehingga
    -1.23
     peuvent
    -1.23
    "
    -1.20
     so
    -1.19
     some
    -1.18
     this
    -1.16
     mogą
    -1.16
    POSITIVE LOGITS
    viles
    1.44
    Andere
    1.28
     вашим
    1.27
    iteľ
    1.24
    vação
    1.23
    Again
    1.23
    代わりに
    1.23
     высоким
    1.23
    Autres
    1.22
    从来
    1.20
    Activations Density 0.024%

    No Known Activations