© 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. 11024
    Prev
    Next
    INDEX
    Explanations

    hidden, unseen, discreet

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

    hidden or invisible

    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
    舺
    0.37
    喳
    0.35
    冝
    0.35
    粔
    0.35
    蛤
    0.34
     ligation
    0.34
     strerror
    0.33
    斛
    0.33
     barro
    0.33
     chir
    0.32
    POSITIVE LOGITS
     hidden
    3.19
    hidden
    2.92
    Hidden
    2.84
     Hidden
    2.81
    隐藏
    2.80
     скры
    2.75
     nascost
    2.75
    隠
    2.66
     invisible
    2.63
    隱
    2.56
    Activations Density 0.940%

    No Known Activations