© 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. 10-GEMMASCOPE-RES-131K
    7. 99507
    Prev
    Next
    INDEX
    Explanations

    maphacks, margin, macosx, maillard, mapreduce, magento

    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_10/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
    榈
    -2.97
    there
    -2.83
    </h3>
    -2.83
    .
    -2.81
    man
    -2.73
    las
    -2.56
    re
    -2.53
    новь
    -2.47
    in
    -2.42
    “,
    -2.36
    POSITIVE LOGITS
    ⇹
    2.53
    いえば
    2.42
    🪆
    2.39
    言えば
    2.33
    𖣔
    2.30
    覚醒
    2.27
    ógy
    2.22
     ворота
    2.19
     be
    2.16
    彞
    2.16
    Activations Density 0.006%

    No Known Activations