© 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. 40-GEMMASCOPE-2-RES-65K
    7. 274
    Prev
    Next
    INDEX
    Explanations

    column with

    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_40_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
    នូវ
    0.26
     এমন
    0.21
    itled
    0.21
    <unused2141>
    0.20
     বলিলেন
    0.19
    だが
    0.19
     başladı
    0.19
     বলিল
    0.19
     deren
    0.19
    曰
    0.19
    POSITIVE LOGITS
     we
    0.54
     they
    0.52
     that
    0.51
     που
    0.51
    that
    0.47
     used
    0.43
     you
    0.43
    ที่
    0.41
     التي
    0.40
     yang
    0.40
    Activations Density 1.731%

    No Known Activations