© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 30113
    Prev
    Next
    INDEX
    Explanations

    Corporation address number

    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
    Negative Logits
    𝓱
    0.38
    啤酒
    0.38
     Implement
    0.37
    --)
    0.37
    剔
    0.37
     follow
    0.35
    _{-}\
    0.35
    Implemented
    0.35
    提起
    0.35
    ombies
    0.35
    POSITIVE LOGITS
    icos
    0.40
    rias
    0.38
     Tob
    0.37
    olina
    0.36
     Pico
    0.36
    ali
    0.36
    lines
    0.36
    reve
    0.36
     Caballero
    0.36
    廖
    0.36
    Activations Density 0.001%

    No Known Activations