© 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. 4899
    Prev
    Next
    INDEX
    Explanations

    phrases with "of"

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

    of [noun/concept]

    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
     peux
    0.23
    ك
    0.23
     posibil
    0.22
    ্রাজ
    0.22
    م
    0.21
     possiamo
    0.21
     reflet
    0.20
    कोलॉजी
    0.20
    टाम
    0.20
    র
    0.20
    POSITIVE LOGITS
    excellence
    0.27
     of
    0.25
    course
    0.24
    ESSION
    0.24
    '
    0.23
    ání
    0.22
    5
    0.22
    ных
    0.22
    ления
    0.22
     учун
    0.22
    Activations Density 0.788%

    No Known Activations