© 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. 181902
    Prev
    Next
    INDEX
    Explanations

    words after "the"

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

    stands for abbreviation explanations

    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
    ка
    0.53
     şə
    0.47
     artifacts
    0.47
    ଶ
    0.46
    ká
    0.45
    命令行
    0.45
     Dij
    0.44
     Ñ
    0.44
    郃
    0.44
     miesto
    0.44
    POSITIVE LOGITS
    imbabwe
    0.48
     தான்
    0.47
     Evol
    0.44
     باك
    0.44
     قرمز
    0.44
     گزینه
    0.44
     출연
    0.43
    ureau
    0.42
    asserie
    0.42
    عبة
    0.42
    Activations Density 0.000%

    No Known Activations