© 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. 7603
    Prev
    Next
    INDEX
    Explanations

    formatting tables

    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
    ាតុ
    0.72
    ោយ
    0.69
     equaling
    0.67
    ามารถ
    0.66
    ្នែក
    0.66
    brightness
    0.66
    :“
    0.65
    اوار
    0.65
     transmittance
    0.64
    <unused706>
    0.64
    POSITIVE LOGITS
     Film
    0.62
    S
    0.62
     |
    0.59
    &#
    0.59
    1
    0.59
     Museum
    0.58
         
    0.58
     Post
    0.57
     Das
    0.57
     Fallout
    0.57
    Activations Density 0.017%

    No Known Activations