© 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. 22-GEMMASCOPE-RES-131K
    7. 54512
    Prev
    Next
    INDEX
    Explanations

    question/answer formats

    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
    attend
    -0.87
    ерез
    -0.84
    seler
    -0.84
    курс
    -0.82
     posando
    -0.82
     médic
    -0.82
    mbangkan
    -0.81
    AddComponent
    -0.81
     grátis
    -0.81
     Podcast
    -0.81
    POSITIVE LOGITS
    lanc
    0.99
     Să
    0.92
     軟
    0.87
    Unione
    0.87
     utopian
    0.85
    榊
    0.84
    帮你
    0.83
     rekan
    0.82
    hart
    0.81
     retire
    0.81
    Activations Density 0.000%

    No Known Activations