© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81675
    Prev
    Next
    INDEX
    Explanations

    edit button

    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
     campionato
    -0.86
    ComponentScan
    -0.81
     rootReducer
    -0.78
    ně
    -0.75
     canina
    -0.73
     about
    -0.73
    ProductCategory
    -0.71
    btnBack
    -0.70
     Made
    -0.70
     Geben
    -0.70
    POSITIVE LOGITS
     edit
    1.54
    edit
    1.51
    Edit
    1.47
     Edit
    1.27
     EDIT
    1.20
     editar
    1.13
     pencil
    1.05
    EDIT
    1.05
    Editar
    1.03
    pencil
    1.03
    Activations Density 0.015%

    No Known Activations