© 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. 33530
    Prev
    Next
    INDEX
    Explanations

    CHECK, apt-get, Copyright, display, code

    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
     their
    -1.07
     taking
    -1.06
     and
    -0.92
    тив
    -0.90
    غال
    -0.88
     such
    -0.88
     ketahui
    -0.87
     with
    -0.86
     very
    -0.84
     bringing
    -0.84
    POSITIVE LOGITS
     stalwart
    1.05
    perity
    1.01
    жнему
    0.96
    linawan
    0.96
    ౮
    0.95
     burner
    0.94
     tandis
    0.94
    isset
    0.94
    ๘
    0.93
    bodyParser
    0.93
    Activations Density 0.007%

    No Known Activations