© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67415
    Prev
    Next
    INDEX
    Explanations

    lengths and widths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ૉ
    -1.55
     garansi
    -1.48
    ּוֹ
    -1.47
    ִּ
    -1.46
     موبایل
    -1.33
     what
    -1.30
     PLAINT
    -1.30
    ֶּ
    -1.30
     seçenek
    -1.30
    וּ
    -1.27
    POSITIVE LOGITS
     ویتامین
    1.34
    ׇ
    1.30
     to
    1.30
     mesmas
    1.30
     deline
    1.24
    有时候
    1.21
    大多
    1.18
     adorned
    1.17
    <em>
    1.17
    स्प
    1.16
    Activations Density 0.010%

    No Known Activations