© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 74920
    Prev
    Next
    INDEX
    Explanations

    introduction and births

    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
    зопас
    -1.25
     their
    -1.16
    ⿻
    -1.06
     would
    -1.05
     both
    -1.00
    july
    -0.99
    ⿷
    -0.96
    :~
    -0.96
     поставить
    -0.96
    -!
    -0.95
    POSITIVE LOGITS
    win
    1.05
    ᗩ
    1.02
    mployed
    1.02
    left
    1.00
     bemerken
    0.97
    poxy
    0.96
    땐
    0.94
    still
    0.93
    sistors
    0.93
    athic
    0.90
    Activations Density 0.000%

    No Known Activations