© 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. 133553
    Prev
    Next
    INDEX
    Explanations

    NIS setup, born, issue, tourism

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

    simple fix, manual deletion

    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
     jama
    0.45
    麻
    0.43
    Б
    0.43
    Jam
    0.43
     и
    0.43
     eta
    0.42
    జా
    0.42
     і
    0.42
     jam
    0.41
    Ja
    0.41
    POSITIVE LOGITS
     extensa
    0.49
     Среди
    0.48
    icing
    0.47
     ஒருவர்
    0.47
    ؍
    0.47
     melodies
    0.47
     પટેલ
    0.46
    ("//
    0.46
     alguém
    0.46
    ים
    0.46
    Activations Density 0.000%

    No Known Activations