© 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. 13-GEMMASCOPE-2-RES-16K
    4. 108
    Prev
    Next
    INDEX
    Explanations

    Fort places

    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
     devoid
    0.59
     a
    0.58
     for
    0.55
     to
    0.54
     we
    0.53
     without
    0.52
    display
    0.51
    :
    0.51
     on
    0.51
     
    0.50
    POSITIVE LOGITS
     gedung
    1.34
     organisasi
    1.32
     pemilihan
    1.31
     komunikasi
    1.30
     secretário
    1.30
     escritório
    1.29
     mahasiswa
    1.27
     presidente
    1.26
     निदेशालय
    1.26
     kantor
    1.24
    Activations Density 0.880%

    No Known Activations