© 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. 27005
    Prev
    Next
    INDEX
    Explanations

    code execution context

    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
     didik
    -1.02
     vokal
    -0.96
     eski
    -0.95
    өздер
    -0.94
    Viited
    -0.94
    legal
    -0.94
     Tämä
    -0.94
     espar
    -0.93
    Etter
    -0.92
    ।
    -0.91
    POSITIVE LOGITS
     then
    1.58
     Then
    1.11
    Then
    1.04
    続いて
    1.00
    続く
    0.98
     continue
    0.93
    then
    0.89
    Howdy
    0.89
     затем
    0.84
    然后再
    0.83
    Activations Density 0.011%

    No Known Activations