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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12193
    Prev
    Next
    INDEX
    Explanations

    july 4th

    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
    naph
    2.69
    م
    2.63
    潢
    2.60
    𝘪
    2.58
    er
    2.56
    ibald
    2.48
    цыя
    2.41
    mang
    2.39
    阱
    2.36
    ain
    2.33
    POSITIVE LOGITS
    ﻝ
    2.93
    <bos>
    2.78
    
    2.71
    ष्क
    2.70
    ẏ
    2.64
    comb
    2.62
    ̈
    2.55
    പ്പെടെ
    2.52
    ॉजिस्ट
    2.50
    ремя
    2.50
    Activations Density 0.029%

    No Known Activations