© 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. 174614
    Prev
    Next
    INDEX
    Explanations

    foreign or ambiguous words

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

    earth passes between sun and moon

    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
     completes
    0.47
     सुधा
    0.47
     पेयजल
    0.46
     教育
    0.46
    飲料
    0.45
     outperforms
    0.44
    낵
    0.44
     ಜನ
    0.44
    🥦
    0.43
    ))$.
    0.43
    POSITIVE LOGITS
     anthropological
    0.45
     otherworldly
    0.43
     archaeological
    0.42
     archae
    0.42
     longe
    0.41
     irgendwie
    0.41
     elast
    0.41
     لحاظ
    0.41
     éch
    0.40
     ambiguous
    0.40
    Activations Density 0.001%

    No Known Activations