© 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. 60439
    Prev
    Next
    INDEX
    Explanations

    suggestions for how to

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

    ideas and how to

    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
    bral
    0.49
    gyro
    0.49
    )#
    0.45
    ♰
    0.45
    )
    0.43
    ставляет
    0.42
    geist
    0.41
    bleeds
    0.41
    )\
    0.41
    ゃ
    0.40
    POSITIVE LOGITS
     bagaimana
    1.01
     how
    0.96
    如何在
    0.91
    如何
    0.91
     কিভাবে
    0.89
     щодо
    0.89
     কীভাবে
    0.88
     كيفية
    0.86
     cómo
    0.84
     如何
    0.82
    Activations Density 0.125%

    No Known Activations