© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14074
    Prev
    Next
    INDEX
    Explanations

    initial, early, first

    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_22/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
     cuối
    -1.10
    最終
    -0.99
     último
    -0.96
     further
    -0.95
     currently
    -0.93
    stals
    -0.90
     possibilità
    -0.86
     τελευτα
    -0.86
     künftig
    -0.85
     Послед
    -0.85
    POSITIVE LOGITS
     initial
    1.44
     primeras
    1.29
     الأولى
    1.22
     Initial
    1.19
     только
    1.16
    Initial
    1.13
     first
    1.12
    initial
    1.10
     eerste
    1.09
     inicial
    1.08
    Activations Density 0.110%

    No Known Activations