© 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. 113279
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases

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

    more semantic implications

    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
     দিচ্ছেন
    0.48
    떻
    0.46
    थर
    0.44
     nondestructive
    0.44
     cea
    0.43
    த்துடன்
    0.42
    quels
    0.42
     deben
    0.42
    ත්ව
    0.41
     connue
    0.40
    POSITIVE LOGITS
     parts
    0.48
    Parts
    0.43
    TI
    0.42
    í
    0.42
    ्ये
    0.41
    ký
    0.41
    ң
    0.41
    to
    0.41
    िट
    0.41
    ية
    0.40
    Activations Density 0.004%

    No Known Activations