© 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. 59913
    Prev
    Next
    INDEX
    Explanations

    in binary or source form

    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
    straining
    -0.79
     quoting
    -0.70
    diendo
    -0.69
    sejarah
    -0.69
    ੨
    -0.68
    ܓ
    -0.67
     steering
    -0.66
    wikidata
    -0.65
    кисло
    -0.65
     usando
    -0.64
    POSITIVE LOGITS
     form
    1.98
     bentuk
    1.74
     forms
    1.61
     dạng
    1.51
     forma
    1.42
    form
    1.38
     formato
    1.36
    的形式
    1.31
     formie
    1.30
     formas
    1.28
    Activations Density 0.108%

    No Known Activations