© 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. 82316
    Prev
    Next
    INDEX
    Explanations

    scope and reach

    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
     indicado
    -1.08
     těchto
    -1.03
     både
    -1.01
     and
    -0.99
     Jordanian
    -0.96
     Tasmanian
    -0.95
     управління
    -0.94
    Locatie
    -0.94
     ($('#
    -0.93
     gekomen
    -0.93
    POSITIVE LOGITS
     elsewhere
    2.45
     beyond
    2.27
     abroad
    2.11
     sekitarnya
    1.78
     surrounding
    1.78
    Elsewhere
    1.63
     Umgebung
    1.59
    beyond
    1.56
     neighboring
    1.55
     neighbouring
    1.55
    Activations Density 0.069%

    No Known Activations