© 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. 111857
    Prev
    Next
    INDEX
    Explanations

    definition and analogy

    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
    ּוֹ
    -2.19
     cán
    -1.95
     bè
    -1.93
     personalización
    -1.86
     gastronomía
    -1.84
     instalación
    -1.84
     construcción
    -1.80
     feil
    -1.79
     zonder
    -1.78
    ִּ
    -1.78
    POSITIVE LOGITS
    ֩
    2.53
     chré
    2.45
     religieux
    2.34
     chrétien
    2.13
    When
    2.11
    ῖν
    2.09
     religieuses
    2.08
     рослин
    2.05
    Although
    2.03
    ῖς
    1.98
    Activations Density 0.090%

    No Known Activations