© 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. 118338
    Prev
    Next
    INDEX
    Explanations

    coin collecting, postal, aviation, banking, applications

    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
     coins
    -1.00
     coin
    -0.91
     quaint
    -0.84
    onomía
    -0.84
    ifero
    -0.83
    груп
    -0.81
    calorie
    -0.81
    🇲
    -0.81
     postage
    -0.80
    𝖺
    -0.77
    POSITIVE LOGITS
    zaak
    0.80
     cong
    0.78
     America
    0.78
     оцени
    0.77
    VERS
    0.77
    olk
    0.75
    ёх
    0.73
    Surely
    0.73
    combined
    0.72
     американ
    0.71
    Activations Density 0.003%

    No Known Activations