© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14710
    Prev
    Next
    INDEX
    Explanations

    Sherbrooke St

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    hnen
    1.07
    Universal
    1.06
    さらに
    1.06
    もっと
    1.05
    s
    1.05
    ová
    1.05
    Multiply
    1.02
    Produ
    1.01
    Currently
    0.99
    Background
    0.98
    POSITIVE LOGITS
     shenanigans
    1.54
     shipment
    1.44
     침
    1.44
     밀
    1.42
     soirée
    1.42
     hapless
    1.41
     consignment
    1.39
     impecc
    1.38
     납
    1.38
     night
    1.38
    Activations Density 0.217%

    No Known Activations