© 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. 75348
    Prev
    Next
    INDEX
    Explanations

    German job postings, plant names, Zeus

    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
    ↵↵
    -2.42
     
    -2.42
     Primarily
    -2.42
    ”
    -2.39
    引き続き
    -2.36
     Mainly
    -2.34
     persever
    -2.34
    経由
    -2.28
     Süden
    -2.25
    ные
    -2.23
    POSITIVE LOGITS
    '
    2.83
     {
    2.72
    </i>
    2.64
     endforeach
    2.63
     {}));
    2.61
    this
    2.53
     détach
    2.33
     Januari
    2.30
     perioden
    2.20
     truk
    2.17
    Activations Density 0.002%

    No Known Activations