© 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. 53973
    Prev
    Next
    INDEX
    Explanations

    documentaries about museums

    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
     terminology
    -0.93
    chita
    -0.89
     suggests
    -0.89
    bbc
    -0.87
     elettrico
    -0.83
     suggestion
    -0.82
     calculations
    -0.82
     imply
    -0.82
     mengatakan
    -0.82
     suggestions
    -0.82
    POSITIVE LOGITS
     chronic
    2.20
     recount
    2.19
    chronic
    2.13
     documenting
    2.06
     detailing
    2.00
     chronicle
    1.94
     chronicles
    1.91
     showcasing
    1.66
    highlight
    1.62
     about
    1.59
    Activations Density 0.182%

    No Known Activations