© 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. 69219
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming constructs

    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
     comiendo
    -1.06
     trataba
    -1.05
     here
    -1.01
     pelig
    -1.00
     at
    -0.98
     its
    -0.96
    mousemove
    -0.96
     well
    -0.95
    ServiceException
    -0.95
     being
    -0.91
    POSITIVE LOGITS
     PRESERV
    1.13
    如果
    1.05
     fiyat
    1.03
     NEGRO
    1.02
     OBJECTIVES
    1.02
    ⓙ
    1.01
    糹
    1.01
    ritsar
    1.01
     REACTION
    1.00
    หมือน
    0.98
    Activations Density 0.001%

    No Known Activations