© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11333
    Prev
    Next
    INDEX
    Explanations

    speeches and presentations

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

    public speaking and presentations

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     屋
    0.44
     خانه
    0.43
     ব্রাজিল
    0.42
    coding
    0.42
     防水
    0.41
     मील
    0.40
     espionage
    0.40
     pinterest
    0.40
     三菱
    0.40
    狩
    0.39
    POSITIVE LOGITS
    演讲
    1.13
     भाषण
    1.02
     orator
    0.99
     বক্তৃতা
    0.98
     speech
    0.97
     speeches
    0.95
     Speech
    0.93
     Presentations
    0.93
    speech
    0.92
    Speech
    0.90
    Activations Density 0.542%

    No Known Activations