© 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. 69824
    Prev
    Next
    INDEX
    Explanations

    words followed by verbs or prepositions

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

    create, track, record, demonstrate, document

    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
    /
    0.63
     Saving
    0.50
    :
    0.46
    igrams
    0.45
    Saving
    0.43
    .}
    0.43
    কেও
    0.43
    म्स
    0.42
    4
    0.42
    ?
    0.42
    POSITIVE LOGITS
     वनस्पती
    0.49
     दस्तावेज
    0.47
    樞
    0.46
     ಪುಸ್ತಕ
    0.46
    目安
    0.45
     bibliothèque
    0.45
    dataTable
    0.45
    ቝ
    0.44
    printer
    0.44
     उत्‍
    0.44
    Activations Density 0.001%

    No Known Activations