© 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. 21807
    Prev
    Next
    INDEX
    Explanations

    job termination

    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
     mxArray
    -1.69
    *}$
    -1.69
    ፑ
    -1.62
    嫆
    -1.59
    *}\
    -1.55
     fraude
    -1.52
    琁
    -1.52
     garantie
    -1.52
     surpre
    -1.48
    ⢪
    -1.48
    POSITIVE LOGITS
     is
    1.52
     واي
    1.44
     dezelfde
    1.41
     ongeveer
    1.30
     slechts
    1.30
     listing
    1.30
     kostenlosen
    1.28
     Româ
    1.28
     mahasiswa
    1.27
     Tentang
    1.25
    Activations Density 0.022%

    No Known Activations