© 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. 36069
    Prev
    Next
    INDEX
    Explanations

    open vs. closed source

    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
     Аб
    0.52
     Ки
    0.49
     Ва
    0.49
     Бар
    0.48
    ᵉ
    0.47
     Hi
    0.47
     нашей
    0.47
     يح
    0.47
     مِن
    0.47
     Вин
    0.47
    POSITIVE LOGITS
    )
    0.50
    Continue
    0.43
     be
    0.42
     advice
    0.42
    ’
    0.40
    )=
    0.39
    祝
    0.39
     leth
    0.39
    Advice
    0.38
    توان
    0.38
    Activations Density 0.006%

    No Known Activations