© 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. 65852
    Prev
    Next
    INDEX
    Explanations

    trained models or weights

    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
    getSystemService
    -1.14
    Ì
    -1.10
    orte
    -1.09
     minutos
    -1.04
    voer
    -1.02
    aire
    -1.02
     طراحی
    -1.01
    edy
    -1.01
     витами
    -1.01
    icus
    -1.00
    POSITIVE LOGITS
     from
    1.15
    Arbe
    1.02
    Fontes
    1.01
    🧫
    0.95
    ʞ
    0.95
     responsabilità
    0.95
    の一つ
    0.95
    omány
    0.94
    メルカリ
    0.94
    呯
    0.94
    Activations Density 0.003%

    No Known Activations