© 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. 22-GEMMASCOPE-RES-131K
    7. 15426
    Prev
    Next
    INDEX
    Explanations

    measurement and approximation

    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_22/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
    ּוֹ
    -1.27
    Selanjutnya
    -1.16
     isolamento
    -1.12
     salário
    -1.12
    ֶּ
    -1.11
    וֹ
    -1.10
    ְּ
    -1.08
    bles
    -1.06
    baiki
    -1.03
     artesanato
    -1.03
    POSITIVE LOGITS
    '=>'
    1.22
     möglichst
    1.08
     "
    1.06
     окружающей
    1.06
     about
    1.05
    を中心に
    1.03
    __',
    1.03
     حدود
    1.03
     Præ
    1.02
     “
    1.02
    Activations Density 0.017%

    No Known Activations