© 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. 35159
    Prev
    Next
    INDEX
    Explanations

    starting with the

    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
    Builders
    0.42
     건설
    0.41
    }});
    0.38
    dinga
    0.38
    sling
    0.37
     बुन्देल
    0.37
    を書
    0.35
    建设
    0.35
    UMIN
    0.35
     انر
    0.35
    POSITIVE LOGITS
    桅
    0.39
     grot
    0.38
    ოს
    0.37
     fighter
    0.36
     모습
    0.36
    道具
    0.36
     realizzato
    0.36
     prop
    0.36
    osition
    0.36
     rocker
    0.36
    Activations Density 0.000%

    No Known Activations