© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54850
    Prev
    Next
    INDEX
    Explanations

    command line program names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تقد
    0.44
    скольку
    0.43
     Waalaikumsalam
    0.40
    匾
    0.40
     _:
    0.39
     MEANS
    0.38
    french
    0.37
     Serpent
    0.37
    icznej
    0.36
     subtree
    0.36
    POSITIVE LOGITS
     උප
    0.41
     अनुकूल
    0.39
     समेत
    0.39
    岫
    0.38
     कार्यरत
    0.38
     கே
    0.37
     نظام
    0.37
    lès
    0.37
    ളി
    0.37
     dein
    0.37
    Activations Density 0.002%

    No Known Activations