© 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. 115753
    Prev
    Next
    INDEX
    Explanations

    used instead

    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
     this
    -1.26
    before
    -1.05
    Before
    -1.05
     Rather
    -1.04
     previous
    -1.02
     similarly
    -1.01
     Again
    -1.00
     zacz
    -0.99
     BEFORE
    -0.98
     Already
    -0.96
    POSITIVE LOGITS
    "../
    1.09
    iële
    1.03
    utriche
    0.99
     čtyř
    0.99
    viève
    0.95
    './
    0.92
    izzata
    0.90
    pM
    0.89
    leda
    0.88
     čty
    0.88
    Activations Density 0.139%

    No Known Activations