© 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. 33756
    Prev
    Next
    INDEX
    Explanations

    word followed by its qualifier

    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
     epidemiology
    -0.86
    $('#
    -0.77
    urgical
    -0.76
     evrops
    -0.76
    localtime
    -0.74
    灘
    -0.73
    åringen
    -0.73
    لت
    -0.73
     during
    -0.72
    འི་
    -0.70
    POSITIVE LOGITS
     expan
    0.86
    binary
    0.81
     thermostat
    0.76
     bub
    0.75
    olute
    0.73
    следова
    0.73
     dll
    0.73
     solute
    0.72
    Binary
    0.72
     Artifacts
    0.72
    Activations Density 0.040%

    No Known Activations