© 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. 103480
    Prev
    Next
    INDEX
    Explanations

    questions and code comments

    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
    花
    -0.81
     moments
    -0.80
     utilizing
    -0.74
     prioritizing
    -0.73
     про
    -0.73
     Calabria
    -0.71
    ย
    -0.71
    izz
    -0.71
    वे
    -0.67
    후
    -0.66
    POSITIVE LOGITS
     Mountaine
    0.94
     svg
    0.89
     mountaine
    0.86
     hydrated
    0.85
     Potomac
    0.85
     Wire
    0.85
    HomeComponent
    0.83
     WIRE
    0.83
    debounce
    0.83
     wire
    0.79
    Activations Density 0.000%

    No Known Activations