© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12366
    Prev
    Next
    INDEX
    Explanations

    web component fragments

    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
     ấy
    2.42
    𝙛
    2.38
    Eyes
    2.38
     prove
    2.36
     faj
    2.32
     Eyes
    2.32
    transport
    2.29
    MODULE
    2.26
    𝙏
    2.24
    مره
    2.23
    POSITIVE LOGITS
    ن
    2.50
    ل
    2.21
     valued
    2.07
    al
    2.07
    aar
    1.99
    efeller
    1.91
    orative
    1.84
    kaar
    1.80
    aus
    1.79
    い
    1.79
    Activations Density 0.012%

    No Known Activations