© 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. 218537
    Prev
    Next
    INDEX
    Explanations

    annual events, appointments, or joining

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

    subscribe hereparticipate incenter lotsallow for

    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
    。
    0.49
    诠
    0.42
    孙
    0.42
    粟
    0.42
    最后一
    0.42
    క
    0.41
     ruth
    0.40
    或者是
    0.40
     wheat
    0.40
    或
    0.39
    POSITIVE LOGITS
    are
    0.50
     limpar
    0.50
     postice
    0.49
    ্তিক
    0.49
    全て
    0.48
     `>`,
    0.48
     எல்லாம்
    0.48
     ஏற்கனவே
    0.48
    არ
    0.47
     Flüss
    0.47
    Activations Density 0.000%

    No Known Activations