© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72611
    Prev
    Next
    INDEX
    Explanations

    common nouns as categories

    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
     and
    -1.14
    不
    -1.09
    韌
    -1.06
    кисло
    -1.05
    テー
    -1.05
     in
    -1.03
     incluso
    -1.00
    энер
    -1.00
    стоит
    -1.00
    レバー
    -0.97
    POSITIVE LOGITS
     more
    1.56
     unterstüt
    1.51
     fewer
    1.45
     than
    1.45
     wtedy
    1.38
     takiego
    1.38
     uscita
    1.37
    .\\
    1.36
     gezwungen
    1.33
     taką
    1.32
    Activations Density 0.100%

    No Known Activations