© 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. 116653
    Prev
    Next
    INDEX
    Explanations

    words ending in -al or -ial

    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
     herói
    -1.10
    linien
    -1.08
    ltä
    -1.01
    lj
    -0.99
     การ
    -0.98
     *>(
    -0.96
    link
    -0.96
    唸
    -0.96
    espresso
    -0.95
     =='
    -0.95
    POSITIVE LOGITS
    ized
    2.25
    ists
    1.88
    ism
    1.83
    ization
    1.78
    ist
    1.67
    ize
    1.61
    ity
    1.55
    izing
    1.51
    isation
    1.50
    istic
    1.46
    Activations Density 0.363%

    No Known Activations