© 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. 27375
    Prev
    Next
    INDEX
    Explanations

    links and urls

    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
    其次
    -1.07
     other
    -0.91
     irgend
    -0.89
     giocatori
    -0.88
    苋
    -0.88
    oléon
    -0.85
     saudável
    -0.85
    ICP
    -0.84
     but
    -0.82
    ={
    -0.82
    POSITIVE LOGITS
     semblables
    1.05
     verhind
    1.00
     incroy
    0.96
    ⑴
    0.96
    網友
    0.95
     monstruos
    0.94
    Première
    0.94
    TRIBUT
    0.94
     maniere
    0.93
     montr
    0.92
    Activations Density 0.012%

    No Known Activations