© 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. 54117
    Prev
    Next
    INDEX
    Explanations

    description

    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
     库存
    -1.15
    Organizador
    -1.09
    Introdução
    -1.09
     DELLE
    -1.08
    *************/
    -1.07
     him
    -1.07
    췄
    -1.07
     rangs
    -1.06
    lorn
    -1.05
    のですね
    -1.05
    POSITIVE LOGITS
     -
    1.47
     is
    1.33
     to
    1.26
     for
    1.25
     détaillés
    1.20
     can
    1.13
     vetores
    1.00
     could
    1.00
    {\
    0.99
     définiti
    0.99
    Activations Density 0.010%

    No Known Activations