© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14059
    Prev
    Next
    INDEX
    Explanations

    byproduct followed by of, arbitrarily close

    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
    ر
    2.71
    ariyati
    2.48
    ikulum
    2.36
    ড়ান্ত
    2.35
    ګه
    2.30
    н
    2.27
    eração
    2.27
    ετε
    2.25
     circunfer
    2.23
    elij
    2.19
    POSITIVE LOGITS
     whor
    2.06
     球
    2.04
    ±
    2.02
     snake
    1.97
    ['
    1.97
    riot
    1.96
     sea
    1.92
     Moon
    1.91
    £
    1.88
    ppo
    1.86
    Activations Density 0.000%

    No Known Activations