© 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. 13-GEMMASCOPE-2-RES-16K
    7. 1995
    Prev
    Next
    INDEX
    Explanations

    see the

    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
    걀
    2.26
    ждением
    2.11
    嘗
    1.98
    sine
    1.96
    cussion
    1.94
    rutt
    1.90
    watering
    1.89
     cư
    1.88
     знаний
    1.87
    topia
    1.87
    POSITIVE LOGITS
    <bos>
    2.19
    ed
    2.04
    fung
    1.98
    ധിപ
    1.91
     szükség
    1.90
    ť
    1.87
    ůj
    1.86
    htra
    1.82
    ht
    1.81
     Spots
    1.81
    Activations Density 0.605%

    No Known Activations