© 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. 31-GEMMASCOPE-2-RES-262K
    7. 83847
    Prev
    Next
    INDEX
    Explanations

    encoded data or representations

    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/layer_31_width_262k_l0_medium
    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
    }-(\
    0.49
    gob
    0.47
    vod
    0.47
    ){
    0.45
    }(
    0.45
    )';
    0.45
    ահ
    0.45
    ')"
    0.45
    ขน
    0.45
    felt
    0.44
    POSITIVE LOGITS
     danni
    0.49
     archival
    0.49
     কমল
    0.48
     щодо
    0.47
     hefty
    0.46
     disposal
    0.46
     livraison
    0.46
     arşiv
    0.45
     ทีม
    0.45
     judiciales
    0.45
    Activations Density 0.006%

    No Known Activations