© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 54287
    Prev
    Next
    INDEX
    Explanations

    prepositions or locative particles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     upang
    -1.05
     tika
    -0.93
    alertDialog
    -0.86
     trong
    -0.85
     μέσα
    -0.85
     Toward
    -0.85
    MOT
    -0.84
     menuju
    -0.84
    alsey
    -0.84
     kapag
    -0.83
    POSITIVE LOGITS
     at
    3.94
    于
    2.38
     aan
    1.82
    於
    1.82
     daran
    1.78
     tại
    1.33
     along
    1.20
     ở
    1.18
     به
    1.10
     στην
    1.09
    Activations Density 0.005%

    No Known Activations