© 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-65K
    7. 2441
    Prev
    Next
    INDEX
    Explanations

    smithsonianmag

    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_65k_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
    С
    1.02
     прибли
    1.02
     Ж
    0.98
     мо
    0.97
    The
    0.94
     Фу
    0.94
     фа
    0.94
     фе
    0.92
    Eng
    0.92
    𝑐
    0.92
    POSITIVE LOGITS
    assies
    1.19
    gdock
    1.14
    leda
    1.09
    <unused1065>
    1.08
    ichern
    1.08
     mixts
    1.08
     predicates
    1.07
    akkhati
    1.07
     merged
    1.06
    ldata
    1.05
    Activations Density 0.103%

    No Known Activations