© 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. 63994
    Prev
    Next
    INDEX
    Explanations

    iterations, variants, Muhammed, red blood cells

    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
    ತ
    0.49
    脍
    0.49
    膾
    0.49
    сро
    0.46
    პირ
    0.41
    三次
    0.41
    ੌਰ
    0.41
    τικο
    0.41
    貫
    0.41
    ﺓ
    0.41
    POSITIVE LOGITS
     bazı
    0.52
     बुरी
    0.52
     richtigen
    0.49
     richtig
    0.45
     někter
    0.45
     niektor
    0.44
     Luigi
    0.43
     těž
    0.43
    ilu
    0.43
     dagli
    0.43
    Activations Density 0.002%

    No Known Activations