© 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. 93035
    Prev
    Next
    INDEX
    Explanations

    am/pm times

    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
     đ
    -0.96
     argentinos
    -0.82
    GQ
    -0.79
     januari
    -0.76
    "</
    -0.75
     Ш
    -0.73
     Presse
    -0.73
    ⌟
    -0.73
    ^{-\
    -0.73
    ける
    -0.73
    POSITIVE LOGITS
    pm
    1.42
     pm
    1.35
     PM
    1.24
    PM
    1.01
     Pm
    0.88
     aprox
    0.84
    sharp
    0.83
     departure
    0.83
    Время
    0.83
     sharp
    0.82
    Activations Density 0.014%

    No Known Activations