© 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. 39707
    Prev
    Next
    INDEX
    Explanations

    Rome itself, School Clean

    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
    ènement
    0.44
    悳
    0.43
    aide
    0.43
    ガー
    0.43
    ⬯
    0.42
     ಸಮಯ
    0.41
    నాన్ని
    0.41
    ・
    0.40
     кере
    0.40
    StudentRecord
    0.40
    POSITIVE LOGITS
     (
    0.42
     plus
    0.42
     mấy
    0.40
     नए
    0.40
     Colorful
    0.40
     consonant
    0.40
     offenses
    0.39
     लड़
    0.39
     enthusi
    0.39
     cotid
    0.38
    Activations Density 0.019%

    No Known Activations