© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67597
    Prev
    Next
    INDEX
    Explanations

    URL query parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     этого
    -1.04
     that
    -1.04
     on
    -1.02
    prende
    -0.93
     Už
    -0.92
     этом
    -0.92
     Russia
    -0.91
    FirebaseDatabase
    -0.89
     ᾿
    -0.86
     Româ
    -0.85
    POSITIVE LOGITS
    providedIn
    1.04
    =
    1.04
     OGSÅ
    1.02
    Джерело
    1.02
    をご覧ください
    1.00
    Поздрав
    1.00
     испы
    0.99
    elseif
    0.98
    Задачи
    0.98
    Secondo
    0.97
    Activations Density 0.070%

    No Known Activations