© 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. 40-GEMMASCOPE-2-RES-262K
    7. 118880
    Prev
    Next
    INDEX
    Explanations

    scales well

    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_40_width_262k_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
    ţia
    0.39
    大致
    0.38
     delve
    0.38
     binding
    0.37
    *,
    0.37
     कस
    0.37
    ılıyor
    0.36
     जल
    0.36
    各自
    0.36
     разработ
    0.36
    POSITIVE LOGITS
    鋏
    0.46
    جن
    0.44
     columnName
    0.42
    collation
    0.41
    normally
    0.41
     tranch
    0.41
     একমাত্র
    0.39
     marido
    0.39
    nows
    0.39
    izophren
    0.38
    Activations Density 0.002%

    No Known Activations