© 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. 13-GEMMASCOPE-2-RES-16K
    7. 6847
    Prev
    Next
    INDEX
    Explanations

    today's context

    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
    ا
    2.54
    ポーツ
    2.31
    ത്തുന്ന
    2.13
    erade
    2.06
    ا۔
    1.99
    ため
    1.88
    hosting
    1.85
    erings
    1.83
    மாகக்
    1.82
    걷
    1.79
    POSITIVE LOGITS
    ्ञ
    2.75
    <bos>
    2.48
     discer
    2.18
    ransport
    1.95
    لل
    1.95
    ل
    1.94
    rj
    1.90
     pomo
    1.85
    奘
    1.83
     pla
    1.81
    Activations Density 0.065%

    No Known Activations