© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 69257
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
    heu
    -1.05
     syk
    -0.96
    TWO
    -0.91
    ENEF
    -0.91
    quels
    -0.89
     bont
    -0.86
    を選び
    -0.85
     lej
    -0.85
     Чем
    -0.84
     linken
    -0.84
    POSITIVE LOGITS
     until
    1.07
     for
    0.98
     without
    0.95
     by
    0.94
     at
    0.94
     some
    0.93
     perhaps
    0.93
     evidently
    0.91
     many
    0.91
     or
    0.91
    Activations Density 0.058%

    No Known Activations