© 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. 116570
    Prev
    Next
    INDEX
    Explanations

    presidential debate

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

    role will, depends on, several options

    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
     Motion
    0.49
     A
    0.48
    统一
    0.47
     Dispose
    0.47
     Sema
    0.47
     سيد
    0.45
     Tableau
    0.45
     Myst
    0.44
     Logger
    0.44
     Deed
    0.44
    POSITIVE LOGITS
    явля
    0.54
     இருக்கலாம்
    0.53
     cubrir
    0.52
    𝗶
    0.52
    ຫຼາຍ
    0.51
    malign
    0.51
     لوبې
    0.50
     मिलने
    0.50
     მისი
    0.50
    accommodation
    0.50
    Activations Density 0.000%

    No Known Activations