© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 210858
    Prev
    Next
    INDEX
    Explanations

    represent and warrant

    np_acts-logits-general · gemini-2.5-flash-lite

    short, explanationcultural contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     meriye
    0.46
     diferença
    0.46
     calcule
    0.44
     יכול
    0.44
    רי
    0.42
     sarà
    0.42
    备份
    0.42
    ҷ
    0.41
     aiuta
    0.41
    ൊപ്പം
    0.40
    POSITIVE LOGITS
    ymmetries
    0.48
     throughout
    0.45
    を通
    0.45
     Cliffs
    0.42
    entation
    0.42
     Oaks
    0.41
     Pto
    0.41
     Dentistry
    0.40
    ंत्रिकी
    0.40
    rzeć
    0.40
    Activations Density 0.000%

    No Known Activations