© 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. 10-GEMMASCOPE-RES-131K
    7. 123913
    Prev
    Next
    INDEX
    Explanations

    fall from, off

    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_10/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
    ჻
    -1.68
    .
    -1.62
     Até
    -1.47
     Otra
    -1.46
    噌
    -1.44
    辞职
    -1.42
    >|
    -1.41
     Temos
    -1.39
     Given
    -1.38
     However
    -1.36
    POSITIVE LOGITS
    </h5>
    1.68
    Deine
    1.49
    甞
    1.41
    Gründe
    1.41
    芣
    1.41
    是多少
    1.40
     hagas
    1.38
    崤
    1.37
    
    1.37
    </i>
    1.37
    Activations Density 0.009%

    No Known Activations