© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15490
    Prev
    Next
    INDEX
    Explanations

    emotions and intense states

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

    flowing course

    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
    Not in Any Lists

    No Comments

    Negative Logits
     somebody
    0.54
     ভাইকে
    0.50
     काबिल
    0.50
    道具
    0.49
     কোনও
    0.48
     کسی
    0.47
     sadistic
    0.47
    某
    0.47
     usando
    0.47
    它可以
    0.46
    POSITIVE LOGITS
     gleaming
    0.51
     silent
    0.50
     strangely
    0.49
     breathless
    0.48
     myriad
    0.48
     shimmering
    0.47
     silenc
    0.47
     streamers
    0.46
     joyous
    0.46
     throng
    0.46
    Activations Density 0.090%

    No Known Activations