© 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. 90351
    Prev
    Next
    INDEX
    Explanations

    `BIT` and `PIN` references

    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
     höhere
    -2.73
    其妙
    -2.61
     impart
    -2.53
    嚒
    -2.50
    脔
    -2.39
     eigentliche
    -2.38
     équipement
    -2.34
     intrigue
    -2.34
    ?’
    -2.33
     intrepid
    -2.31
    POSITIVE LOGITS
    e
    3.83
    ه
    3.73
    er
    3.55
    ed
    3.28
    o
    3.06
    n
    3.03
    h
    2.39
    »
    2.39
    g
    2.39
    ו
    2.38
    Activations Density 0.002%

    No Known Activations