© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115969
    Prev
    Next
    INDEX
    Explanations

    award counts and nominations

    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
     Nobel
    -1.34
    Nobel
    -1.31
     Oscars
    -0.85
     annunci
    -0.84
     conduc
    -0.82
    Noble
    -0.79
     noblesse
    -0.76
     positron
    -0.75
     GOAT
    -0.74
     desco
    -0.74
    POSITIVE LOGITS
     award
    1.55
     Award
    1.27
    award
    1.10
     Emmy
    1.10
    Award
    0.96
     published
    0.90
     AWARD
    0.90
     National
    0.89
     national
    0.88
     successful
    0.84
    Activations Density 0.054%

    No Known Activations