© 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. 70550
    Prev
    Next
    INDEX
    Explanations

    disease, computing, economics, groups

    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
     eksklu
    -1.01
    fortnite
    -0.99
    indonesia
    -0.97
     Suicide
    -0.93
     poft
    -0.92
    gigi
    -0.92
     poliuret
    -0.91
     köy
    -0.90
     astronom
    -0.90
    frases
    -0.90
    POSITIVE LOGITS
     can
    0.86
     und
    0.83
    the
    0.82
     has
    0.82
     setups
    0.81
    leville
    0.81
    ↴
    0.81
     ↑
    0.81
     [
    0.81
     also
    0.80
    Activations Density 0.319%

    No Known Activations