© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129210
    Prev
    Next
    INDEX
    Explanations

    recent trouble and events

    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
     a
    -1.15
     cuando
    -1.08
    了一眼
    -1.07
     was
    -1.05
     queste
    -1.04
     zulassen
    -1.02
     cuya
    -1.00
     eines
    -0.99
     década
    -0.99
     when
    -0.98
    POSITIVE LOGITS
     recent
    1.84
     lately
    1.58
    recent
    1.51
    Recent
    1.34
     regarding
    1.31
    Recently
    1.31
     اخیر
    1.31
     everyone
    1.30
     recently
    1.24
    RECENT
    1.18
    Activations Density 0.058%

    No Known Activations