© 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. 25980
    Prev
    Next
    INDEX
    Explanations

    key and legend explanations

    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
    LocationManager
    -0.94
    顧
    -0.81
    рых
    -0.78
     Nacionales
    -0.76
     sacerdote
    -0.74
    δρ
    -0.73
    addComponent
    -0.71
    FormState
    -0.71
     Stimme
    -0.71
    おはよう
    -0.71
    POSITIVE LOGITS
     legend
    3.89
     Legend
    3.47
     key
    3.41
    legend
    3.25
    Legend
    3.25
    key
    2.92
     legends
    2.89
     keys
    2.88
     Key
    2.83
    Key
    2.78
    Activations Density 0.046%

    No Known Activations