© 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. 131036
    Prev
    Next
    INDEX
    Explanations

    College and research

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

    pronouns followed by verbs or prepositions

    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
     மூன்று
    0.52
     அலங்க
    0.51
     تعلیم
    0.50
     تربیت
    0.48
    脿
    0.48
     অংশে
    0.47
     چنین
    0.47
     समर्पण
    0.47
    cyan
    0.46
     وفق
    0.46
    POSITIVE LOGITS
    (
    0.50
     mls
    0.44
     roll
    0.44
     rollover
    0.43
     saud
    0.43
     hele
    0.43
     renters
    0.43
     prosecutions
    0.43
    flix
    0.42
     loses
    0.42
    Activations Density 0.001%

    No Known Activations