© 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. 34-GEMMASCOPE-RES-131K
    7. 59824
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and variables

    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_34/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
    Other
    -0.90
     dazzling
    -0.88
    ᐈ
    -0.87
    してみると
    -0.86
     evaluation
    -0.84
     stately
    -0.84
    смотрим
    -0.84
     other
    -0.81
    諳
    -0.80
    bleau
    -0.80
    POSITIVE LOGITS
     ridiculously
    0.96
     presque
    0.89
    RIQUE
    0.88
    primarily
    0.85
     spearheaded
    0.84
     exceptionally
    0.84
     obf
    0.80
    ądz
    0.80
     SPECIAL
    0.79
     insanely
    0.79
    Activations Density 0.044%

    No Known Activations