© 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. 239451
    Prev
    Next
    INDEX
    Explanations

    policy statement, advent calendars, Caribbean bowler

    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
     空
    0.50
     menyel
    0.48
     monarch
    0.48
     沒有
    0.47
     S
    0.46
     చెప్పు
    0.46
     Center
    0.45
     造
    0.45
     中心
    0.45
     中央
    0.45
    POSITIVE LOGITS
    慨
    0.52
    خرى
    0.49
     metabolized
    0.45
     vectorized
    0.45
     संस्कार
    0.44
     इंटीग्र
    0.43
    ​)
    0.42
    ٹھ
    0.42
     قانونی
    0.42
     نتی
    0.41
    Activations Density 0.000%

    No Known Activations