© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 65801
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by context

    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_22/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
     diesen
    -1.07
    ägg
    -1.05
     skóra
    -0.97
     Iš
    -0.95
     bestellen
    -0.94
     seyn
    -0.93
     embalagem
    -0.90
    pozycji
    -0.89
     fufficient
    -0.88
    Câ
    -0.87
    POSITIVE LOGITS
     to
    1.37
     by
    1.16
     and
    1.05
    hatenablog
    1.01
     with
    1.00
    Nhưng
    0.98
    activités
    0.98
     or
    0.96
    』『
    0.94
     sebagai
    0.94
    Activations Density 0.141%

    No Known Activations