© 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. 47649
    Prev
    Next
    INDEX
    Explanations

    Tweaks, Black Americans, Prime, testimony, People tried

    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
    ὠ
    0.45
     ధ
    0.41
     उन्मूलन
    0.40
    ड़
    0.40
     स्क्रीन
    0.40
     vực
    0.40
    idcoin
    0.39
     concerted
    0.39
    ває
    0.39
    ถูกต้อง
    0.38
    POSITIVE LOGITS
     amphibians
    0.45
    preparing
    0.42
    。（
    0.40
     lipids
    0.39
    preparation
    0.39
    அ
    0.38
    緊急
    0.38
     acoustics
    0.38
     barrels
    0.38
     Cly
    0.38
    Activations Density 0.009%

    No Known Activations