© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 10999
    Prev
    Next
    INDEX
    Explanations

    prepositions or common verbs followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_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
    Ві
    0.82
    
    0.80
     Utilisez
    0.80
     алыңыз
    0.80
    سرائيل
    0.78
     ישראל
    0.75
    lí
    0.75
    НЫ
    0.75
    ÉN
    0.73
    
    0.73
    POSITIVE LOGITS
     upto
    1.68
     equipments
    1.52
     atleast
    1.51
     evidences
    1.27
     topmost
    1.24
     saree
    1.16
     sarees
    1.14
     softwares
    1.12
     bollywood
    1.11
     wastage
    1.10
    Activations Density 0.001%

    No Known Activations