© 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. 2652
    Prev
    Next
    INDEX
    Explanations

    logic and math abbreviations

    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
    pentru
    -0.80
    Jah
    -0.79
    年後
    -0.78
    (>
    -0.73
     slike
    -0.73
    ۱۱
    -0.73
    esseur
    -0.72
    referral
    -0.71
    catalogue
    -0.70
     AKP
    -0.70
    POSITIVE LOGITS
    hah
    0.78
     shorter
    0.76
     conclusion
    0.75
     abbre
    0.74
    transform
    0.74
    temon
    0.73
    tem
    0.72
     etmek
    0.71
     abbreviation
    0.69
    Uy
    0.69
    Activations Density 0.019%

    No Known Activations