© 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-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13882
    Prev
    Next
    INDEX
    Explanations

    outro

    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
    ństw
    3.20
    DebugSymbols
    2.92
    wyczaj
    2.86
    粵
    2.63
    ecção
    2.59
     рабочей
    2.51
     Букмекерская
    2.50
    DefinitionGroup
    2.48
    jeto
    2.47
    WebV
    2.44
    POSITIVE LOGITS
    ামুটি
    2.72
    ielle
    2.57
    ок
    2.51
    ing
    2.24
    ா
    2.14
     stockings
    2.13
    ು
    2.10
    Purs
    2.10
    濂
    2.09
    лох
    2.09
    Activations Density 0.002%

    No Known Activations