© 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. 34-GEMMASCOPE-RES-131K
    7. 107935
    Prev
    Next
    INDEX
    Explanations

    months and days

    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_34/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
    One
    -1.11
     één
    -1.03
     one
    -1.02
     One
    -1.02
     אחד
    -0.94
     ONE
    -0.91
    ワン
    -0.91
     один
    -0.84
     both
    -0.82
     satu
    -0.81
    POSITIVE LOGITS
     two
    0.98
     segundo
    0.87
     second
    0.86
     ۲
    0.84
     twos
    0.82
    殊
    0.82
    二是
    0.81
    two
    0.81
     zwei
    0.81
    deux
    0.81
    Activations Density 0.167%

    No Known Activations