© 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. 34-GEMMASCOPE-RES-131K
    7. 53910
    Prev
    Next
    INDEX
    Explanations

    importance of, considerably from

    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
     so
    -1.18
     in
    -1.17
     two
    -1.05
     four
    -1.02
     three
    -0.98
     for
    -0.96
     or
    -0.95
     six
    -0.94
     still
    -0.93
     eight
    -0.91
    POSITIVE LOGITS
     substan
    0.99
     hefty
    0.94
    çamento
    0.90
    olid
    0.89
    tries
    0.89
     aktiviert
    0.85
    剛剛
    0.85
     obvio
    0.84
     sugges
    0.84
     crea
    0.82
    Activations Density 0.000%

    No Known Activations