© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13290
    Prev
    Next
    INDEX
    Explanations

    median age, duration, or count

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

    solving algebraic equations

    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_16k_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
    인지
    0.43
    મિ
    0.43
    थान
    0.41
    。"
    0.40
    主动
    0.38
    ."-
    0.38
    omi
    0.38
     谢
    0.38
     SalesLT
    0.37
    rya
    0.37
    POSITIVE LOGITS
    sufficiency
    0.48
     maire
    0.44
    وند
    0.43
     perfect
    0.42
     availed
    0.42
     quies
    0.42
     punctul
    0.41
     heer
    0.41
     travail
    0.41
     outil
    0.41
    Activations Density 0.021%

    No Known Activations