© 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. 22-GEMMASCOPE-RES-131K
    7. 67855
    Prev
    Next
    INDEX
    Explanations

    special linguistic or structural markers

    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_22/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
    いただける
    -1.20
    肌肤
    -1.16
    xpress
    -1.16
     if
    -1.16
     there
    -1.11
    asının
    -1.09
    czych
    -1.05
    淠
    -1.03
     correspondingly
    -1.03
     Ähn
    -1.03
    POSITIVE LOGITS
    mathrm
    1.17
    ;</
    1.14
    》、《
    1.13
    </h4>
    1.07
    >
    1.02
     achet
    1.02
     handen
    1.00
     détruire
    1.00
     bestaande
    1.00
     besucht
    1.00
    Activations Density 0.000%

    No Known Activations