© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 292
    Prev
    Next
    INDEX
    Explanations

    moving outwards or towards

    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
    繁忙時間服務
    0.44
     advantageous
    0.43
    requent
    0.43
    ีก
    0.43
     এইরূপে
    0.43
    }');
    0.43
     eux
    0.41
    ῇ
    0.41
    รรม
    0.41
    予防
    0.40
    POSITIVE LOGITS
     into
    0.90
     back
    0.78
     towards
    0.67
    into
    0.66
     down
    0.63
     onto
    0.63
     hacia
    0.63
     toward
    0.62
     inwards
    0.61
     إلى
    0.59
    Activations Density 0.008%

    No Known Activations