© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9280
    Prev
    Next
    INDEX
    Explanations

    URLs with YouTube links

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

    for _ in range

    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
    </
    0.39
    װ
    0.39
    eball
    0.39
    ◉
    0.39
    ◙
    0.38
    ٭
    0.38
    。「
    0.37
    㼛
    0.37
    ◎
    0.36
    FIG
    0.36
    POSITIVE LOGITS
     _
    2.47
     (_
    2.05
    (_
    2.00
    ._
    1.98
     _)
    1.91
    ,_
    1.89
     _,
    1.84
     "_
    1.81
     '_
    1.78
    =_
    1.77
    Activations Density 0.045%

    No Known Activations