© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 10598
    Prev
    Next
    INDEX
    Explanations

    measures, time, record, universities

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

    news announcements and events

    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_40_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
     🥰
    1.43
     проє
    1.42
    🥰
    1.35
     ২০২২
    1.34
     проєкту
    1.33
    🥹
    1.30
     ২০২৩
    1.27
    🫶
    1.26
    https
    1.21
    🥲
    1.21
    POSITIVE LOGITS
    
    0.96
     http
    0.85
    http
    0.81
     इलाहाबाद
    0.71
     Orissa
    0.65
    􀂃
    0.64
     ২০১০
    0.63
     চিকিত
    0.62
     spokeswoman
    0.58
    ऎ
    0.58
    Activations Density 0.248%

    No Known Activations