© 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-65K
    7. 40107
    Prev
    Next
    INDEX
    Explanations

    northern Kosovo

    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_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
    ແບບ
    0.52
     لق
    0.50
    機會
    0.49
    សូម
    0.47
     fifty
    0.46
     ه
    0.46
     کام
    0.46
     cân
    0.46
    <unused1079>
    0.46
     abrir
    0.45
    POSITIVE LOGITS
    ுள்ளனர்
    0.41
    oscale
    0.41
     Venkates
    0.41
     cycled
    0.38
    hanam
    0.37
    sti
    0.37
     circuitry
    0.37
    is
    0.37
    胝
    0.37
     Connell
    0.37
    Activations Density 0.005%

    No Known Activations