© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2260
    Prev
    Next
    INDEX
    Explanations

    negations of exactly, really

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     bc
    0.87
     cuz
    0.83
     since
    0.83
     ALSO
    0.82
     savior
    0.79
    —-
    0.77
    ---
    0.75
    --->
    0.75
    
    0.75
     walmart
    0.73
    POSITIVE LOGITS
    Really
    1.28
    really
    1.25
     Really
    1.23
     really
    1.18
     surely
    1.08
     vraiment
    1.04
     reckons
    1.02
     determinadas
    1.00
    Surely
    0.99
     wirklich
    0.99
    Activations Density 0.230%

    No Known Activations