© 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. 116979
    Prev
    Next
    INDEX
    Explanations

    Millennials, YouTubers, Harris

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

    determiner or pronoun followed by adjective

    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
     hacerlo
    0.45
     उसमे
    0.44
     他
    0.43
     也
    0.43
     them
    0.42
    里面
    0.42
     них
    0.41
     但
    0.41
    で
    0.40
    又
    0.39
    POSITIVE LOGITS
     Millennials
    0.34
     YouTuber
    0.34
     livestream
    0.33
     Harris
    0.33
     Diploma
    0.32
    များသည်
    0.32
     millennials
    0.32
     commemorating
    0.31
     ఇటీవల
    0.31
     commemorative
    0.31
    Activations Density 0.118%

    No Known Activations