© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27767
    Prev
    Next
    INDEX
    Explanations

    randomized controlled trial

    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
     from
    -1.26
     trabaja
    -1.05
    n
    -1.02
    rías
    -1.02
    textnormal
    -1.00
    w
    -0.98
    omaly
    -0.98
     since
    -0.97
     trovato
    -0.96
     jesteśmy
    -0.94
    POSITIVE LOGITS
     isEqualToString
    1.09
    เลือก
    1.05
     objectForKey
    1.03
    خانه
    1.02
     发表于
    0.98
     consciente
    0.98
     disputa
    0.96
     COUNCIL
    0.95
     randomized
    0.94
    ALOG
    0.94
    Activations Density 0.149%

    No Known Activations