© 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. 21151
    Prev
    Next
    INDEX
    Explanations

    unique and distinct options

    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
     seal
    0.55
     unable
    0.55
     customs
    0.50
     broker
    0.48
     bean
    0.48
     tires
    0.48
    在
    0.46
     in
    0.46
    X
    0.46
     drinks
    0.45
    POSITIVE LOGITS
    فتح
    0.53
     እነ
    0.47
    㖮
    0.46
     इमरजेंसी
    0.45
     एनएस
    0.45
     abrió
    0.45
     відкри
    0.44
     Öff
    0.43
     откры
    0.43
     Ministério
    0.43
    Activations Density 0.020%

    No Known Activations