© 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. 40779
    Prev
    Next
    INDEX
    Explanations

    symbolic gestures, key concepts

    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
     caters
    0.48
     savory
    0.46
     fat
    0.43
     catering
    0.43
     catered
    0.41
     colch
    0.41
     glycoproteins
    0.40
    鹸
    0.40
     gifting
    0.39
     lợi
    0.39
    POSITIVE LOGITS
    怀疑
    0.46
    Clause
    0.45
    跇
    0.43
     परिजन
    0.43
    ようになった
    0.43
    教师
    0.42
    老师
    0.42
     ongeveer
    0.42
    出现
    0.41
    NgramModel
    0.41
    Activations Density 0.000%

    No Known Activations