© 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. 108005
    Prev
    Next
    INDEX
    Explanations

    honors and recognition

    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
     امريكا
    -0.73
    JsonObject
    -0.73
    ₺
    -0.72
     spikes
    -0.71
     abide
    -0.69
     Corintios
    -0.69
    assic
    -0.68
     Más
    -0.68
    ônus
    -0.68
     rhetor
    -0.68
    POSITIVE LOGITS
     Birthday
    1.36
    Birthday
    1.23
     Honors
    1.19
     honours
    1.16
     honors
    1.13
     Honours
    1.12
     Queen
    1.06
    Queen
    1.02
     birthday
    1.01
     recognition
    1.00
    Activations Density 0.035%

    No Known Activations