© 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. 72136
    Prev
    Next
    INDEX
    Explanations

    future plans and actions

    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
    stände
    -1.07
    饬
    -1.05
    coda
    -0.96
     Komunikasi
    -0.95
    ſo
    -0.94
    asında
    -0.94
    鎳
    -0.93
    diyesi
    -0.93
    issez
    -0.91
    kiwa
    -0.91
    POSITIVE LOGITS
     will
    2.66
     plans
    1.67
     already
    1.62
    将会
    1.39
     would
    1.37
     Already
    1.36
     proposal
    1.30
     plan
    1.29
     sẽ
    1.28
     nantinya
    1.28
    Activations Density 0.067%

    No Known Activations