© 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. 22-GEMMASCOPE-RES-131K
    7. 36261
    Prev
    Next
    INDEX
    Explanations

    map and for loops

    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
    Formazione
    -1.24
     Kō
    -1.10
    kungen
    -1.05
     Spanyol
    -1.02
     mecan
    -0.99
     konsult
    -0.98
     kaas
    -0.96
    TextHelper
    -0.96
     exercices
    -0.94
     asti
    -0.94
    POSITIVE LOGITS
     recently
    1.06
     last
    1.05
     his
    1.04
    *,
    1.02
     ’
    0.96
     recent
    0.96
     (
    0.95
    recently
    0.95
     Oct
    0.95
    Recently
    0.94
    Activations Density 0.002%

    No Known Activations