© 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. 62920
    Prev
    Next
    INDEX
    Explanations

    internet slang and exclamations

    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
     Covid
    -1.30
     COVID
    -1.29
    ״
    -1.08
    й
    -1.07
     covid
    -1.07
    }&
    -0.98
    absl
    -0.95
    ️
    -0.92
     \%)$
    -0.91
     our
    -0.88
    POSITIVE LOGITS
    inb
    1.25
    Derp
    1.20
     lul
    1.16
     SCIENCE
    1.09
     manly
    1.09
    orz
    1.09
     nao
    1.09
    hipster
    1.08
     hipster
    1.05
    lul
    1.05
    Activations Density 0.128%

    No Known Activations