© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 10562
    Prev
    Next
    INDEX
    Explanations

    numbers and code segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    齙
    0.41
    гія
    0.40
    炁
    0.40
    了一眼
    0.38
    chyné
    0.38
    र्फ
    0.37
    ској
    0.36
    CONFIGURE
    0.35
    禳
    0.35
    侈
    0.35
    POSITIVE LOGITS
     fifteen
    0.55
     fourteen
    0.55
     twenty
    0.54
     thirty
    0.50
    0.48
     sixteen
    0.45
     eighteen
    0.45
     eleven
    0.44
     sixty
    0.43
     thirteen
    0.43
    Activations Density 0.075%

    No Known Activations