© 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. 200590
    Prev
    Next
    INDEX
    Explanations

    predicated upon, condemns, Shark Week

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

    year, month, Korea, Taiwan

    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
     fuller
    0.48
    㹮
    0.48
     heathen
    0.46
     polynucle
    0.46
     священ
    0.46
    ;-
    0.44
     volant
    0.44
    醂
    0.44
     quisquam
    0.43
     redshifts
    0.42
    POSITIVE LOGITS
     year
    0.49
     Korea
    0.49
    msub
    0.47
     বছর
    0.44
    ao
    0.43
    Korea
    0.43
     month
    0.43
     QQ
    0.42
    year
    0.41
     Year
    0.41
    Activations Density 0.001%

    No Known Activations