© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13608
    Prev
    Next
    INDEX
    Explanations

    network

    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
    𝐚
    2.86
    𝐡
    2.78
    𝐞
    2.69
    𝐢
    2.58
    𝐠
    2.58
    𝐨
    2.46
    𝐟
    2.40
    𝐮
    2.39
    𝐦
    2.27
    𝐫
    2.24
    POSITIVE LOGITS
    iados
    2.76
    eqnarray
    2.70
    aient
    2.65
     Під
    2.64
     damos
    2.61
    oł
    2.60
    JJ
    2.60
    RAW
    2.54
    udarstvennyj
    2.53
    ဝင်
    2.52
    Activations Density 0.001%

    No Known Activations