© 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. 27040
    Prev
    Next
    INDEX
    Explanations

    filename, key, sample, password, json

    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
     మనం
    0.45
    鹦
    0.39
    ંદ્ર
    0.38
    কেবল
    0.38
    您可以
    0.37
     செயலாளர்
    0.35
     पोकेमॉन
    0.35
    বিত্র
    0.35
     указыва
    0.35
     삽니다
    0.34
    POSITIVE LOGITS
     successfully
    0.40
     both
    0.39
     op
    0.38
     ý
    0.38
     முறை
    0.38
     vies
    0.38
     både
    0.37
     laik
    0.37
     différent
    0.37
    により
    0.37
    Activations Density 0.102%

    No Known Activations