© 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. 1404
    Prev
    Next
    INDEX
    Explanations

    protect and enhance

    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
    cloak
    2.57
     față
    2.42
    ০০
    2.40
    𝘄
    2.38
     cuest
    2.37
     *\
    2.35
    ead
    2.33
    รง
    2.32
    ee
    2.32
    cellaneous
    2.31
    POSITIVE LOGITS
    DEFGHIJKLMNOP
    2.79
    ა
    2.66
    कुंठ
    2.50
    DEFGHI
    2.50
     rato
    2.38
    𝒟
    2.38
    ėl
    2.36
    ąz
    2.36
    acyl
    2.32
    র
    2.28
    Activations Density 0.373%

    No Known Activations