© 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. 71878
    Prev
    Next
    INDEX
    Explanations

    words followed by conjunctions

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

    code structure or technical terms

    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
    پی
    0.50
    гло
    0.47
    د
    0.47
    ಯ
    0.45
    遠
    0.45
    ප
    0.44
    쎄
    0.44
    し
    0.44
    изо
    0.44
    い
    0.44
    POSITIVE LOGITS
     Frege
    0.54
     Hypertension
    0.51
     NRI
    0.50
     ABV
    0.50
     खुशखबरी
    0.49
     MBA
    0.48
     REIT
    0.48
     kHz
    0.48
     KCl
    0.48
     Keluarga
    0.47
    Activations Density 0.002%

    No Known Activations