© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1643
    Prev
    Next
    INDEX
    Explanations

    example usage

    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_17_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
     быть
    1.09
    ′
    1.09
    could
    1.08
     Could
    1.08
    त्रेयी
    1.06
    UNITED
    1.05
    Could
    1.05
    泺
    1.02
    €™
    1.01
    ﺷ
    1.01
    POSITIVE LOGITS
     selalu
    1.16
    oughby
    1.14
    上下
    1.06
    킵
    1.05
    amette
    1.04
    IAMS
    1.04
    永遠
    1.03
     tentu
    1.01
     never
    1.00
     seldom
    0.99
    Activations Density 0.421%

    No Known Activations