© 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. 22-GEMMASCOPE-RES-131K
    7. 27561
    Prev
    Next
    INDEX
    Explanations

    code keywords and syntax

    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
     salvajes
    -0.99
     impresionantes
    -0.98
    以外の
    -0.96
     メール
    -0.90
     nadru
    -0.88
    Czym
    -0.87
    킵
    -0.87
     соотно
    -0.86
     содержание
    -0.86
     człowiek
    -0.86
    POSITIVE LOGITS
     by
    1.11
    áne
    1.09
     itens
    1.05
    riva
    1.05
    oxia
    1.03
     aparelho
    1.00
     sério
    0.99
    резать
    0.98
    철
    0.96
    atase
    0.95
    Activations Density 0.045%

    No Known Activations