© 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. 9396
    Prev
    Next
    INDEX
    Explanations

    boolean flags and states

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

    boolean logic and conditions

    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
    🏞
    0.40
    ન્દ
    0.39
     뭐라고
    0.38
    ધન
    0.38
    తర
    0.38
    魟
    0.38
    neho
    0.37
    轟
    0.37
    轰
    0.37
    㷅
    0.37
    POSITIVE LOGITS
     boolean
    2.13
    boolean
    2.05
    Boolean
    2.03
     Boolean
    2.02
     bool
    1.88
    bool
    1.87
     BOOLE
    1.80
     Bool
    1.79
    BOOLE
    1.77
    Bool
    1.73
    Activations Density 0.108%

    No Known Activations