© 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. 124024
    Prev
    Next
    INDEX
    Explanations

    introducing or defining terms

    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
     любых
    -1.25
    袒
    -1.24
    сль
    -1.22
     lacks
    -1.21
     MINUTE
    -1.20
    じっくり
    -1.20
    ◍
    -1.18
     insofar
    -1.16
     ця
    -1.15
    没有什么
    -1.15
    POSITIVE LOGITS
     a
    1.90
     called
    1.84
    called
    1.48
     referred
    1.41
     Called
    1.40
     we
    1.40
     our
    1.36
     rencont
    1.34
    Called
    1.30
     an
    1.28
    Activations Density 0.211%

    No Known Activations