© 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. 2782
    Prev
    Next
    INDEX
    Explanations

    how to use

    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
     pertenecen
    1.13
    landscape
    1.07
     padrões
    0.99
    uniform
    0.99
    prints
    0.98
     pertenece
    0.98
    顷
    0.96
    प्रिय
    0.95
    cheek
    0.94
    had
    0.93
    POSITIVE LOGITS
    回事
    1.27
    겼
    1.11
    分辨
    1.09
     circumvent
    1.08
    对待
    1.08
     getInput
    1.07
    ETARY
    1.07
     quantified
    1.07
    iliated
    1.07
    ೃದ್ಧ
    1.06
    Activations Density 0.661%

    No Known Activations