© 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. 38175
    Prev
    Next
    INDEX
    Explanations

    opening quotes

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

    It, I, we start speaking

    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
     reverts
    0.42
     করিবেন
    0.41
    менно
    0.40
     hasht
    0.39
     [[[
    0.39
     affording
    0.39
     compels
    0.39
     presently
    0.38
    Dichloro
    0.38
    ]);}
    0.38
    POSITIVE LOGITS
    didn
    0.54
     lihtsalt
    0.53
     potem
    0.52
     Потом
    0.51
    rible
    0.49
     It
    0.49
     herkes
    0.47
     ഡ്ര
    0.47
     afterward
    0.46
    riving
    0.46
    Activations Density 0.011%

    No Known Activations