© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123899
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
    {
    -2.44
     However
    -1.66
     What
    -1.65
    .
    -1.60
    ↵↵
    -1.55
     To
    -1.55
     The
    -1.53
     Another
    -1.53
    <sup>
    -1.52
     to
    -1.52
    POSITIVE LOGITS
    vierten
    1.80
    焢
    1.75
    紲
    1.74
     kutu
    1.71
    úmenes
    1.66
     mauva
    1.64
    𝅥
    1.62
    idades
    1.59
    liehen
    1.59
     rése
    1.55
    Activations Density 0.015%

    No Known Activations