© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81137
    Prev
    Next
    INDEX
    Explanations

    scoring

    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
     arreglar
    -0.88
    戶
    -0.83
     Congrats
    -0.82
    geolocation
    -0.81
     Thiru
    -0.81
    endió
    -0.77
     zy
    -0.76
    Oster
    -0.75
    箱
    -0.74
     orilla
    -0.74
    POSITIVE LOGITS
     scoring
    1.41
    scoring
    1.34
    Scoring
    1.02
     scores
    0.86
    scores
    0.85
     score
    0.85
     poj
    0.85
     Scoring
    0.82
    coring
    0.81
    score
    0.79
    Activations Density 0.008%

    No Known Activations