© 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. 69270
    Prev
    Next
    INDEX
    Explanations

    management, planning, research, automation

    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
    simov
    -1.43
    えっ
    -1.38
     numerous
    -1.36
    romas
    -1.34
    isling
    -1.33
     that
    -1.32
     the
    -1.30
    rafat
    -1.30
     or
    -1.30
    etna
    -1.27
    POSITIVE LOGITS
    <bos>
    1.28
     Palabra
    1.25
    şit
    1.19
     PETER
    1.19
    panes
    1.16
    entrySet
    1.16
    もう
    1.15
    และ
    1.13
    QUÉ
    1.13
     skills
    1.12
    Activations Density 0.061%

    No Known Activations