© 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. 16047
    Prev
    Next
    INDEX
    Explanations

    new year resolutions

    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
    Goodnight
    -1.16
    ಿದ
    -1.13
     enjeux
    -1.11
     snel
    -1.08
    Когда
    -1.04
    Alternatives
    -1.03
    eventually
    -1.02
    Ģ
    -1.02
    laatst
    -1.01
    ridae
    -1.01
    POSITIVE LOGITS
     new
    1.82
     year
    1.48
     årets
    1.47
    新的
    1.42
     change
    1.30
     January
    1.30
     anew
    1.27
     nový
    1.24
    新
    1.23
    ာ
    1.20
    Activations Density 0.040%

    No Known Activations