© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11414
    Prev
    Next
    INDEX
    Explanations

    IEEE Transactions

    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
    dır
    3.07
    ｬ
    2.94
    ු
    2.87
    nade
    2.75
    م
    2.57
     судо
    2.50
    ो
    2.50
    kannya
    2.46
    ことにより
    2.41
    𝘢
    2.40
    POSITIVE LOGITS
    た
    2.77
    ,))
    2.74
    ᑲ
    2.63
    ूर्त
    2.44
    fully
    2.36
    řel
    2.30
    ্যাল
    2.30
     combs
    2.29
    <!--
    2.23
     merhaba
    2.23
    Activations Density 0.010%

    No Known Activations