© 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. 118313
    Prev
    Next
    INDEX
    Explanations

    per the

    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
    istical
    -1.10
     noin
    -1.07
    日を
    -1.02
    atge
    -1.01
    などが
    -0.99
    罰
    -0.98
     semua
    -0.98
     tất
    -0.95
    賃
    -0.95
     segala
    -0.94
    POSITIVE LOGITS
     their
    2.09
     the
    1.84
     your
    1.63
     what
    1.60
     our
    1.56
     different
    1.50
     circumstances
    1.45
     prevailing
    1.42
     dictates
    1.34
     which
    1.23
    Activations Density 0.045%

    No Known Activations