© 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. 22720
    Prev
    Next
    INDEX
    Explanations

    numeric lists with commas

    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
     sque
    0.39
    🥇
    0.37
    べき
    0.36
     practically
    0.36
     Equ
    0.36
     elimination
    0.36
    Margins
    0.35
     experienced
    0.35
     Evaluation
    0.35
     portfolios
    0.35
    POSITIVE LOGITS
    mainloop
    0.41
     अर्ध
    0.40
    opacity
    0.40
    ivam
    0.39
     pres
    0.39
     faibles
    0.38
     faible
    0.38
    劏
    0.38
     regina
    0.38
    incar
    0.38
    Activations Density 0.003%

    No Known Activations