© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11309
    Prev
    Next
    INDEX
    Explanations

    expressions of liking or preference

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

    offering to do something for user

    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
    ू
    0.62
    reqParams
    0.50
     Trade
    0.49
    ⮚
    0.48
    
    0.46
    便利な
    0.46
     ビタミン
    0.43
     Hometown
    0.43
    ▸
    0.42
    ⊖
    0.42
    POSITIVE LOGITS
     minded
    0.67
    minded
    0.56
    不喜欢
    0.48
    Liked
    0.48
    inded
    0.48
    warz
    0.46
     liking
    0.45
    hearted
    0.45
    ни
    0.44
    weaver
    0.44
    Activations Density 0.084%

    No Known Activations