© 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. 19964
    Prev
    Next
    INDEX
    Explanations

    liability for loss or damage

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

    more capable, find Lena

    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
     дене
    0.48
    ંબા
    0.46
    缺点
    0.46
    视野
    0.43
    饲
    0.42
     Rxe
    0.42
    so
    0.40
    ่น
    0.40
    轧
    0.40
    "।
    0.39
    POSITIVE LOGITS
    cję
    0.43
     shaping
    0.41
     symb
    0.40
    €”
    0.39
    ––
    0.39
     sympath
    0.39
     dart
    0.39
     stocking
    0.38
     மணி
    0.38
     المؤ
    0.38
    Activations Density 0.001%

    No Known Activations