© 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-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 135133
    Prev
    Next
    INDEX
    Explanations

    past participles or prepositions following verbs

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

    describing something following a word

    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
    লেক
    0.47
    ابية
    0.47
    illage
    0.45
     '">'
    0.42
    いている
    0.41
    illow
    0.41
    w
    0.40
     selected
    0.39
    Willow
    0.39
    ://$
    0.38
    POSITIVE LOGITS
     வசன
    0.52
     ઇ
    0.48
     geliştir
    0.48
     ugljik
    0.47
     enzim
    0.46
    cogn
    0.45
     Senin
    0.45
     ecuaciones
    0.44
     dérivés
    0.44
     Nuevo
    0.44
    Activations Density 0.001%

    No Known Activations