© 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. 39045
    Prev
    Next
    INDEX
    Explanations

    current events and time periods

    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
     from
    -1.27
    ↵↵↵
    -1.21
    ↵↵↵↵↵↵
    -1.20
     in
    -1.17
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -1.16
    ↵↵↵↵
    -1.16
    ↵↵↵↵↵
    -1.16
    ↵↵↵↵↵↵↵↵
    -1.14
    onesian
    -1.12
    ↵↵↵↵↵↵↵↵↵↵
    -1.08
    POSITIVE LOGITS
     we
    2.30
     our
    2.20
     everyone
    2.09
     everybody
    1.95
     μας
    1.72
    是我们
    1.51
     naše
    1.51
    我們
    1.49
    everyone
    1.48
    Our
    1.48
    Activations Density 0.025%

    No Known Activations