© 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-16K
    7. 10307
    Prev
    Next
    INDEX
    Explanations

    positive sentiment emojis

    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_16k_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
    aaaa
    0.44
    积
    0.44
    ⚖
    0.44
    ☀️
    0.43
    ()*
    0.42
     :)
    0.41
    ílio
    0.41
    ϟ
    0.41
    끗
    0.40
    🔥
    0.39
    POSITIVE LOGITS
     technically
    0.46
     urč
    0.45
     precis
    0.42
     referencia
    0.42
     le
    0.41
     cultura
    0.41
     defini
    0.41
     unusually
    0.40
     defens
    0.40
     dec
    0.40
    Activations Density 0.026%

    No Known Activations