© 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. 27714
    Prev
    Next
    INDEX
    Explanations

    State, version, or number followed by colon

    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
     Contains
    -0.98
    ませて
    -0.90
    お世話
    -0.89
     explic
    -0.88
    pertur
    -0.88
     εικό
    -0.85
     gră
    -0.85
    ItemType
    -0.85
     même
    -0.84
     baloncesto
    -0.83
    POSITIVE LOGITS
    漬
    0.93
    &=&
    0.89
     are
    0.87
     of
    0.87
     ContentValues
    0.84
    すな
    0.83
     disclosed
    0.83
    ﴿
    0.82
     ayude
    0.80
     зима
    0.79
    Activations Density 0.027%

    No Known Activations