© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 6564
    Prev
    Next
    INDEX
    Explanations

    United Nations

    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_all/layer_41_width_262k_l0_big
    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
     adjustable
    0.48
     equaling
    0.45
     equivalently
    0.44
    ម្លៃ
    0.44
    <unused311>
    0.44
     ถ้า
    0.44
     isotropic
    0.44
    <unused2175>
    0.44
    対処
    0.43
     textured
    0.43
    POSITIVE LOGITS
    in
    0.50
    com
    0.46
    Med
    0.45
    Leggi
    0.45
    k
    0.44
    K
    0.44
    Forum
    0.44
    Еще
    0.44
    en
    0.43
    on
    0.42
    Activations Density 0.000%

    No Known Activations