© 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. 75506
    Prev
    Next
    INDEX
    Explanations

    tattoo and variations

    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
    forma
    -0.90
    ({'
    -0.87
    ::*;
    -0.87
     automation
    -0.84
     UnityEngine
    -0.84
    ctive
    -0.83
     Tenis
    -0.82
    unref
    -0.78
     frizz
    -0.77
     Automation
    -0.76
    POSITIVE LOGITS
     tattoo
    3.84
     tattoos
    3.41
     Tattoo
    2.88
    tattoo
    2.75
     tattooed
    2.61
    Tattoo
    2.58
     Tattoos
    2.45
    attoos
    2.00
     tatu
    1.89
     татуи
    1.79
    Activations Density 0.032%

    No Known Activations