© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65326
    Prev
    Next
    INDEX
    Explanations

    ban moratorium halt freeze

    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
     acestui
    -0.85
    ार्
    -0.76
    ローチ
    -0.72
    apparition
    -0.72
    iedene
    -0.71
    uchtigkeit
    -0.71
    مدر
    -0.71
    decoded
    -0.71
    escaped
    -0.69
     acestei
    -0.68
    POSITIVE LOGITS
     moratorium
    3.03
     freeze
    2.34
     ban
    2.25
    freeze
    1.76
     mor
    1.74
    Freeze
    1.64
    Mor
    1.63
     Freeze
    1.62
     Mor
    1.59
     freezes
    1.59
    Activations Density 0.034%

    No Known Activations