© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 770
    Prev
    Next
    INDEX
    Explanations

    real time

    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_34/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
    ahuje
    -0.99
    extremely
    -0.84
     выпуск
    -0.83
    several
    -0.83
    ggers
    -0.82
    ongoing
    -0.79
     귀
    -0.79
     langer
    -0.78
    یش
    -0.77
    itisation
    -0.75
    POSITIVE LOGITS
     time
    2.73
    time
    1.75
     времени
    1.49
     real
    1.37
    Time
    1.33
     Time
    1.33
     tiempo
    1.32
     near
    1.23
    TIME
    1.20
    Время
    1.18
    Activations Density 0.013%

    No Known Activations