© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3838
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating topic

    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_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
    }$.
    0.24
    ج
    0.23
    י
    0.22
    threaded
    0.22
    achelors
    0.22
     მაგრამ
    0.20
    renner
    0.20
    router
    0.20
    ります
    0.20
    ี
    0.20
    POSITIVE LOGITS
     về
    0.27
    :
    0.25
     поводу
    0.25
     about
    0.25
    n
    0.24
     việc
    0.24
    此事
    0.24
     tentang
    0.23
     tacos
    0.22
     a
    0.22
    Activations Density 0.359%

    No Known Activations