© 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-65K
    7. 708
    Prev
    Next
    INDEX
    Explanations

    flowing downhill

    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_65k_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
    ב
    0.72
    ي
    0.67
    も
    0.66
    يمكن
    0.64
    י
    0.61
    도
    0.61
    ال
    0.56
    ה
    0.55
    أ
    0.54
    catalyzed
    0.53
    POSITIVE LOGITS
     spiller
    0.60
    et
    0.52
     synchron
    0.51
     seda
    0.47
    </h1>
    0.46
     de
    0.46
     konk
    0.46
     parli
    0.46
    ier
    0.45
    uste
    0.44
    Activations Density 1.208%

    No Known Activations