© 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. 1595
    Prev
    Next
    INDEX
    Explanations

    "previous" or related to things that happened before

    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
     |=
    0.90
    finally
    0.86
     everyday
    0.86
    Feet
    0.82
     uiteindelijk
    0.82
     daily
    0.82
     Sain
    0.82
    Ƹ
    0.81
     finally
    0.80
     விளங்க
    0.80
    POSITIVE LOGITS
     previous
    2.95
    previous
    2.78
     sebelumnya
    2.71
     предыду
    2.60
     anteriores
    2.58
    Previous
    2.57
     anteriormente
    2.50
     Previous
    2.50
     previously
    2.45
     précédemment
    2.45
    Activations Density 2.441%

    No Known Activations