© 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. 70595
    Prev
    Next
    INDEX
    Explanations

    real, true, accurate

    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
     to
    -1.08
     sagt
    -1.07
    IRED
    -0.99
     în
    -0.99
     who
    -0.97
     così
    -0.94
     spéc
    -0.94
    &
    -0.93
     umfass
    -0.93
     verschieden
    -0.92
    POSITIVE LOGITS
     adanya
    1.09
    Maka
    1.04
     tacón
    1.04
    內的
    1.02
     ביותר
    1.00
    اريخ
    0.99
    থ্য
    0.98
     nabíd
    0.97
     cromado
    0.96
     antiquated
    0.96
    Activations Density 0.027%

    No Known Activations