© 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. 1781
    Prev
    Next
    INDEX
    Explanations

    Tag Archives

    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
    ּוֹ
    -2.22
    ֶּ
    -1.98
    ִּ
    -1.82
    ְּ
    -1.77
     étages
    -1.68
    ַּ
    -1.65
     πρ
    -1.63
     but
    -1.62
     who
    -1.59
     here
    -1.59
    POSITIVE LOGITS
    ׇ
    2.53
     چربی
    1.91
     nutrisi
    1.77
    ὴν
    1.77
     گیاه
    1.74
    ᾷ
    1.67
     regiones
    1.65
     namor
    1.57
     atitude
    1.56
    ଼
    1.52
    Activations Density 0.156%

    No Known Activations