© 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. 75575
    Prev
    Next
    INDEX
    Explanations

    referring to previously mentioned items

    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
     juiste
    -2.23
    渽
    -1.98
     persoonlijke
    -1.80
     afgelopen
    -1.74
     entweder
    -1.69
    struzioni
    -1.67
    쨩
    -1.66
     zarówno
    -1.65
     şeyler
    -1.65
     secluded
    -1.64
    POSITIVE LOGITS
    商城
    1.48
     –
    1.48
     namn
    1.45
     spela
    1.45
     trev
    1.41
    tação
    1.41
    作为
    1.37
    “
    1.37
     bottes
    1.37
    towy
    1.36
    Activations Density 0.012%

    No Known Activations