© 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. 49626
    Prev
    Next
    INDEX
    Explanations

    resume, campaigns, phones, sessions

    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
     Ос
    0.54
    ikt
    0.52
    可愛
    0.45
     可愛
    0.45
    utzt
    0.45
     світ
    0.44
    📢
    0.44
    ün
    0.43
    orton
    0.43
    dk
    0.43
    POSITIVE LOGITS
    徒歩
    0.49
    ：
    0.45
    ；
    0.45
     dù
    0.44
    が入
    0.44
    なら
    0.43
    ）；
    0.43
     přest
    0.42
    、
    0.42
     dhammo
    0.42
    Activations Density 0.001%

    No Known Activations