© 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. 33253
    Prev
    Next
    INDEX
    Explanations

    defining concepts and their relationships

    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
     Behör
    -1.04
    umbra
    -0.93
     Θε
    -0.91
    autres
    -0.89
    ritsar
    -0.85
    ₩
    -0.85
    umpulan
    -0.84
    maq
    -0.84
    快乐
    -0.83
     selezion
    -0.83
    POSITIVE LOGITS
     having
    1.71
     belonging
    1.39
     lacking
    1.31
    having
    1.30
     capable
    1.22
     something
    1.15
     requiring
    1.14
     relating
    1.14
     ayant
    1.14
     resembling
    1.13
    Activations Density 0.023%

    No Known Activations