© 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. 10-GEMMASCOPE-RES-131K
    7. 113129
    Prev
    Next
    INDEX
    Explanations

    last of phrases

    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_10/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
     These
    -1.74
    銩
    -1.70
     Эти
    -1.63
     vry
    -1.62
    ズニー
    -1.49
     präsenti
    -1.49
     Socialism
    -1.48
    raszam
    -1.48
     extro
    -1.47
     exertions
    -1.45
    POSITIVE LOGITS
    乄
    1.77
    goes
    1.66
    “
    1.62
    臵
    1.61
     about
    1.55
    咗
    1.54
    骉
    1.54
     decide
    1.52
    gives
    1.51
     Versuch
    1.51
    Activations Density 0.002%

    No Known Activations