© 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. 22-GEMMASCOPE-RES-131K
    4. 131005
    Prev
    Next
    INDEX
    Explanations

    names and titles after punctuation

    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
    June
    -1.05
    July
    -1.04
     June
    -1.02
    September
    -0.97
     fermé
    -0.97
     January
    -0.93
    𝐓
    -0.93
    January
    -0.91
    白色
    -0.91
    recent
    -0.89
    POSITIVE LOGITS
     at
    1.03
     while
    1.01
    日に
    0.90
    ឡ
    0.90
    cciones
    0.90
     after
    0.89
     ayı
    0.89
    hysema
    0.89
     після
    0.88
    tamaan
    0.88
    Activations Density 0.017%

    No Known Activations