© 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. 31-GEMMASCOPE-2-RES-262K
    7. 125139
    Prev
    Next
    INDEX
    Explanations

    dictionary definitions

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

    contextual structural markers

    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_31_width_262k_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
    ![](
    0.49
    ｲ
    0.49
    yección
    0.46
    +}$
    0.46
    執行
    0.46
     underlie
    0.43
    }^{
    0.43
    IRQ
    0.43
    úly
    0.42
     ਰ
    0.42
    POSITIVE LOGITS
     navigable
    0.50
     salesperson
    0.48
     servants
    0.46
     pleated
    0.46
     traders
    0.45
     luggage
    0.43
     salespeople
    0.43
     oficial
    0.43
     negotiated
    0.43
     negotiable
    0.43
    Activations Density 0.001%

    No Known Activations