© 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. 873
    Prev
    Next
    INDEX
    Explanations

    code initialization and data handling

    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
     kunnen
    -1.19
    甗
    -1.18
    Industries
    -1.17
    跸
    -1.17
     unſ
    -1.16
    讦
    -1.11
    客气
    -1.09
     houſe
    -1.09
     نقطة
    -1.08
     mily
    -1.07
    POSITIVE LOGITS
     mostly
    1.38
     mainly
    1.30
     adaptée
    1.27
     various
    1.23
     aspects
    1.22
    Before
    1.20
     Initially
    1.17
     establishes
    1.15
     markedly
    1.13
     primarily
    1.11
    Activations Density 0.067%

    No Known Activations