© 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. 16-GEMMASCOPE-2-RES-262K
    7. 42126
    Prev
    Next
    INDEX
    Explanations

    debug mode

    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_16_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
     a
    0.88
    1
    0.80
     you
    0.74
    är
    0.72
     the
    0.71
     maupun
    0.71
    eds
    0.71
    ang
    0.70
    4
    0.70
    apa
    0.69
    POSITIVE LOGITS
    ي
    1.09
    ك
    1.04
    л
    1.02
    ла
    0.97
    ل
    0.90
    ה
    0.89
    ות
    0.87
    이사
    0.87
    ने
    0.85
    ال
    0.82
    Activations Density 0.012%

    No Known Activations