© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13854
    Prev
    Next
    INDEX
    Explanations

    enzyme

    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
    द्धांत
    2.55
    oxel
    2.47
    <bos>
    2.45
    val
    2.29
    MLE
    2.28
    ழுது
    2.24
    radian
    2.21
    abases
    2.17
    czas
    2.13
    ო
    2.12
    POSITIVE LOGITS
    AndKeys
    2.82
    叠
    2.77
    araj
    2.68
     deix
    2.65
    وست
    2.65
    ὗ
    2.63
     deixa
    2.57
    /******/
    2.55
    মুনা
    2.49
    脲
    2.42
    Activations Density 0.015%

    No Known Activations