© 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. 160627
    Prev
    Next
    INDEX
    Explanations

    white jeans

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

    explanation for understanding

    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
     ovens
    0.46
    岧
    0.45
    診療
    0.44
     shampoos
    0.44
     steels
    0.43
     ယ
    0.42
    iums
    0.42
     earths
    0.42
    iseconds
    0.41
    就
    0.41
    POSITIVE LOGITS
    profile
    0.50
     folgt
    0.48
     folgender
    0.47
     Produkt
    0.47
     suivante
    0.47
    พา
    0.46
    pillar
    0.46
     sommes
    0.45
     محصول
    0.45
     सेमीफाइनल
    0.45
    Activations Density 0.000%

    No Known Activations