© 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. 59069
    Prev
    Next
    INDEX
    Explanations

    technical terms and names

    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
    ∊
    -0.78
    KeyPressed
    -0.76
     miners
    -0.75
    ױ
    -0.75
     Auburn
    -0.72
    anto
    -0.72
     Flach
    -0.72
    ⓘ
    -0.71
    巫
    -0.71
    ":
    -0.70
    POSITIVE LOGITS
     datastore
    0.94
    Extent
    0.81
    CAND
    0.80
     biele
    0.78
    тивный
    0.77
     candidates
    0.76
    Nucle
    0.76
    SLO
    0.75
     奈
    0.75
     gql
    0.75
    Activations Density 0.013%

    No Known Activations