© 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. 13-GEMMASCOPE-2-RES-16K
    7. 8525
    Prev
    Next
    INDEX
    Explanations

    math formulas

    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_13_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
     howling
    2.26
    𝐡
    2.10
     treaty
    2.10
    ಲ್ಲಿ
    2.09
     sine
    2.06
    ্লেখ
    2.06
     doorbell
    2.02
     sewer
    2.00
     attire
    1.99
     autumnal
    1.98
    POSITIVE LOGITS
    nå
    2.81
    هن
    2.36
    zett
    2.22
    zés
    2.22
    nach
    2.20
    رک
    2.19
    ي
    2.18
    ('')
    2.18
    z
    2.12
     फीसदी
    2.12
    Activations Density 0.009%

    No Known Activations