© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 9320
    Prev
    Next
    INDEX
    Explanations

    assignment operator in code

    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
     foster
    1.93
     dep
    1.91
     tick
    1.88
    ଡ
    1.84
     "**
    1.78
     為
    1.72
     "***
    1.72
    ত
    1.71
    ли
    1.70
    ous
    1.69
    POSITIVE LOGITS
    <blockquote>
    2.68
    ﻯ
    2.15
    ंपल
    2.04
    ᖁ
    2.03
    ء
    1.99
    ższ
    1.99
    ="#!"
    1.96
    เอ
    1.94
    żej
    1.93
    ทยา
    1.92
    Activations Density 0.008%

    No Known Activations