© 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. 22-GEMMASCOPE-RES-131K
    4. 74014
    Prev
    Next
    INDEX
    Explanations

    parts or remainder

    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_22/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
    endlich
    -1.05
    lossene
    -0.99
     medición
    -0.99
    visits
    -0.98
    cricket
    -0.95
     espesor
    -0.95
     взгля
    -0.94
    Agregar
    -0.94
    indest
    -0.94
     resistir
    -0.93
    POSITIVE LOGITS
     for
    1.40
     to
    1.34
    を
    1.32
    それを
    1.03
     of
    1.02
     做
    0.97
    住院
    0.97
     back
    0.95
    これを
    0.94
     prud
    0.94
    Activations Density 0.026%

    No Known Activations