© 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. 16121
    Prev
    Next
    INDEX
    Explanations

    numbers and identifiers

    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
    ের
    3.50
    ي
    3.40
    ی
    3.40
    as
    3.05
    ා
    3.05
    ا
    3.04
    in
    2.92
    る
    2.90
    <bos>
    2.89
    ০
    2.79
    POSITIVE LOGITS
    ॉफ्ट
    2.49
    Whole
    2.37
    mentation
    2.35
    𝚞
    2.25
    Habitat
    2.20
    Prima
    2.19
    ণ্ঠে
    2.19
    ibility
    2.19
    ίνη
    2.19
    굵
    2.19
    Activations Density 0.165%

    No Known Activations