© 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. 241795
    Prev
    Next
    INDEX
    Explanations

    escape category, booking system

    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
     tz
    0.54
    o
    0.50
     อำ
    0.49
    m
    0.49
    tz
    0.48
     cau
    0.48
    reached
    0.47
    a
    0.47
    moved
    0.47
     dhad
    0.46
    POSITIVE LOGITS
    ین
    0.66
     분포
    0.50
    ات
    0.46
    ને
    0.46
     चैप्टर्स
    0.45
    ホルダー
    0.43
     ग्रोथ
    0.42
     Canadian
    0.41
    idays
    0.41
    ب
    0.40
    Activations Density 0.001%

    No Known Activations