© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 59914
    Prev
    Next
    INDEX
    Explanations

    prepositions to/from/on/connecting places

    np_acts-logits-general · gemini-2.5-flash-lite

    Get all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    m
    0.56
    ti
    0.51
    pro
    0.50
    n
    0.50
    al
    0.50
    rou
    0.49
    ty
    0.49
    it
    0.49
    on
    0.49
    li
    0.49
    POSITIVE LOGITS
     quinoa
    0.56
    🧖
    0.53
    推出了
    0.51
    வர்களின்
    0.51
    ўкі
    0.50
    쫀득
    0.50
     ставки
    0.49
     millennials
    0.49
     các
    0.48
     крупных
    0.48
    Activations Density 0.000%

    No Known Activations