© 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. 3663
    Prev
    Next
    INDEX
    Explanations

    words starting with st

    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
    2
    1.34
    ,
    1.28
    6
    1.24
    5
    1.23
    9
    1.09
    ள்
    1.00
    هاي
    0.98
    7
    0.97
    ת
    0.95
    ها
    0.93
    POSITIVE LOGITS
     도시
    0.91
     آئے
    0.90
     광
    0.89
     ویب
    0.88
     출연
    0.88
     스트
    0.86
     grava
    0.86
     علی
    0.85
     fortes
    0.85
     اسٹ
    0.85
    Activations Density 0.199%

    No Known Activations