© 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. 34-GEMMASCOPE-RES-131K
    7. 2618
    Prev
    Next
    INDEX
    Explanations

    noun phrases with qualifiers

    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
    bekistan
    -1.32
     ২০১
    -1.13
     bilgisayar
    -1.10
    ૉ
    -1.10
    大満足
    -1.09
     gostar
    -1.07
    Etimo
    -1.04
     rajut
    -1.03
     pôr
    -1.01
     heilige
    -1.00
    POSITIVE LOGITS
     AEG
    1.02
     tuberculosis
    1.02
     telegraph
    0.98
     radium
    0.95
     KD
    0.95
    ქ
    0.94
     Jewish
    0.93
     PTT
    0.93
     sten
    0.93
     Meteoro
    0.93
    Activations Density 0.114%

    No Known Activations