© 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. 34-GEMMASCOPE-RES-131K
    4. 83882
    Prev
    Next
    INDEX
    Explanations

    part or portion

    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_34/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
    (++
    -0.94
     каждом
    -0.91
    твра
    -0.89
    forto
    -0.85
     fiecare
    -0.85
    igerung
    -0.85
    angor
    -0.83
     ufficiale
    -0.83
    beleid
    -0.83
     тях
    -0.82
    POSITIVE LOGITS
     part
    7.25
     часть
    5.22
    part
    4.97
    部分
    4.84
     части
    4.78
     parts
    4.72
     portions
    4.63
     portion
    4.59
     część
    4.28
     części
    4.25
    Activations Density 0.448%

    No Known Activations