© 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. 86654
    Prev
    Next
    INDEX
    Explanations

    describing categories and attributes

    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
     from
    -1.57
     they
    -1.53
     using
    -1.41
    日起
    -1.36
     that
    -1.25
     Dicapai
    -1.24
    ți
    -1.23
     mereka
    -1.23
    меди
    -1.20
    믿
    -1.19
    POSITIVE LOGITS
     wtedy
    1.66
     itself
    1.63
     zawsze
    1.48
     anunció
    1.46
    Where
    1.45
    itself
    1.45
     revisa
    1.43
     its
    1.42
     både
    1.41
    provides
    1.41
    Activations Density 0.701%

    No Known Activations