© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 903
    Prev
    Next
    INDEX
    Explanations

    assembly, Issue, doc, InlineData, TestFixture, Route, Struct, Treatment

    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
    ’
    -1.87
    等は
    -1.79
     are
    -1.70
     You
    -1.58
    にした
    -1.53
    出了一
    -1.50
    了一会儿
    -1.48
    愉
    -1.48
    などなど
    -1.46
    などは
    -1.41
    POSITIVE LOGITS
     it
    2.88
     these
    1.83
     any
    1.81
     residing
    1.77
     this
    1.75
     If
    1.74
    今では
    1.70
    Pgina
    1.70
    筚
    1.64
     you
    1.63
    Activations Density 0.004%

    No Known Activations