© 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. 40500
    Prev
    Next
    INDEX
    Explanations

    technical documents or projects

    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
    WARDS
    -1.09
    taya
    -1.09
    +</
    -1.09
    REME
    -1.08
    ถ้า
    -1.07
    íč
    -1.05
    isms
    -1.05
    """"
    -1.04
    gered
    -1.03
    {{-
    -1.03
    POSITIVE LOGITS
     as
    1.46
     Jurí
    1.38
     murieron
    1.34
     any
    1.33
     deberán
    1.27
    توض
    1.21
     recibieron
    1.16
     which
    1.15
     dissolves
    1.15
    Visión
    1.14
    Activations Density 0.282%

    No Known Activations