© 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. 2822
    Prev
    Next
    INDEX
    Explanations

    adjective

    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
     milliliters
    0.49
     ezingu
    0.47
    ggbb
    0.47
     compresses
    0.47
     authorizations
    0.46
     niž
    0.46
    フォーマンス
    0.46
    }^{+}+\
    0.46
     miljoen
    0.45
    MILLISE
    0.45
    POSITIVE LOGITS
     adjective
    0.74
     being
    0.66
     Being
    0.64
     быть
    0.61
    Being
    0.59
     Truly
    0.55
    Truly
    0.55
    being
    0.55
     bersifat
    0.55
     adjectives
    0.54
    Activations Density 0.005%

    No Known Activations