© 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. 1533
    Prev
    Next
    INDEX
    Explanations

    found or exists

    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
     себя
    0.73
     остальные
    0.62
    ся
    0.62
     ajo
    0.61
    َهُ
    0.61
     эти
    0.60
     אות
    0.59
    ются
    0.59
     нему
    0.58
     voices
    0.58
    POSITIVE LOGITS
     ausschließlich
    1.19
    ङ
    1.18
     splike
    1.09
     characterized
    1.07
     primarily
    1.05
     combining
    1.05
     unui
    1.05
    <unused1856>
    1.03
     독
    1.02
     terdiri
    1.02
    Activations Density 0.301%

    No Known Activations