© 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. 15237
    Prev
    Next
    INDEX
    Explanations

    new type of

    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
    ujesz
    -1.34
     roulant
    -1.27
     bailando
    -1.25
    焌
    -1.15
    着一
    -1.15
     enamorado
    -1.13
    phòng
    -1.13
    都知道
    -1.10
    bàn
    -1.09
     sonriendo
    -1.06
    POSITIVE LOGITS
     другие
    1.35
     andere
    1.34
     in
    1.18
    hender
    1.17
     других
    1.16
     …)
    1.13
     anderen
    1.12
     other
    1.11
     will
    1.09
     其他
    1.09
    Activations Density 0.168%

    No Known Activations