© 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
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11116
    Prev
    Next
    INDEX
    Explanations

    action followed by context

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

    how things manifest or happen

    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
     invari
    0.56
     wholeheartedly
    0.56
    䒷
    0.55
     during
    0.54
     earnestly
    0.53
     shortly
    0.53
    が通販
    0.53
    几年
    0.52
     anonymously
    0.52
    墂
    0.52
    POSITIVE LOGITS
    0.61
     S
    0.55
    Y
    0.50
    G
    0.47
     G
    0.46
     R
    0.46
    Info
    0.45
    R
    0.45
     V
    0.45
    V
    0.44
    Activations Density 0.085%

    No Known Activations