© 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. 129359
    Prev
    Next
    INDEX
    Explanations

    recent past 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
     also
    -1.11
     with
    -1.00
     Also
    -0.98
     so
    -0.94
    signol
    -0.94
     también
    -0.92
     também
    -0.90
    also
    -0.88
     Wär
    -0.85
     także
    -0.85
    POSITIVE LOGITS
     recently
    1.52
     yesterday
    1.38
     earlier
    1.15
    recently
    1.05
     recentemente
    1.03
    Recently
    0.98
     Thursday
    0.98
     recém
    0.97
    Earlier
    0.97
     Wednesday
    0.96
    Activations Density 0.131%

    No Known Activations