© 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. 75821
    Prev
    Next
    INDEX
    Explanations

    flexibility or inhibitors

    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
    uniqueItems
    0.48
    ᕇ
    0.46
    滀
    0.45
    क्षणिक
    0.45
    颶
    0.45
    㗁
    0.45
    OGRAPHIC
    0.44
    њи
    0.44
    Normalization
    0.44
    othérapie
    0.43
    POSITIVE LOGITS
     to
    0.49
    ur
    0.47
    า
    0.46
     where
    0.45
     protagonistas
    0.45
    ien
    0.45
     |
    0.45
     ayuda
    0.45
     rod
    0.44
     or
    0.44
    Activations Density 0.001%

    No Known Activations