© 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. 92312
    Prev
    Next
    INDEX
    Explanations

    former vs latter

    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
     escaleras
    -1.24
    ctuaries
    -1.19
     peinados
    -1.16
     faldas
    -1.16
     huellas
    -1.09
     pensamientos
    -1.09
    GLY
    -1.08
     colgantes
    -1.06
    ごとの
    -1.06
     tatuajes
    -1.05
    POSITIVE LOGITS
     one
    1.90
     option
    1.63
     of
    1.55
     opción
    1.27
    者
    1.24
     type
    1.18
     scenario
    1.16
     two
    1.12
    option
    1.09
     category
    1.09
    Activations Density 0.063%

    No Known Activations