© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 16836
    Prev
    Next
    INDEX
    Explanations

    urination and bodily functions

    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
     garg
    0.45
     spher
    0.43
     homestead
    0.42
     cosm
    0.42
     ceram
    0.41
    .**
    0.41
    arche
    0.41
     comprador
    0.40
     spheroid
    0.40
     questo
    0.40
    POSITIVE LOGITS
    нет
    0.56
    
    0.56
    ны
    0.51
    та
    0.49
    ាទ
    0.48
     ปลา
    0.48
     गोपनीय
    0.47
    ॔
    0.47
     नियंत्रित
    0.47
    ш
    0.47
    Activations Density 0.005%

    No Known Activations