© 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. 75807
    Prev
    Next
    INDEX
    Explanations

    determine the principal end

    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
    ія
    -0.86
    勫
    -0.82
    onHide
    -0.79
     ось
    -0.77
    最早
    -0.77
     ditu
    -0.75
    JUD
    -0.75
    нович
    -0.75
    𝕋
    -0.75
     DISPOSAL
    -0.74
    POSITIVE LOGITS
    Doubt
    0.83
    memorial
    0.83
    洵
    0.80
     ergänzt
    0.76
    Nonsense
    0.76
    ྣ
    0.75
     خواهید
    0.75
    Sighs
    0.75
     Referenzen
    0.75
     keines
    0.73
    Activations Density 0.041%

    No Known Activations