© 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. 41362
    Prev
    Next
    INDEX
    Explanations

    religious figures and texts

    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
     use
    -1.26
    。「
    -1.09
     \
    -1.08
    solete
    -1.07
    Emm
    -1.04
    於
    -1.04
    ，「
    -1.02
    一時
    -1.02
    spesies
    -1.01
     et
    -1.00
    POSITIVE LOGITS
    χρι
    1.43
    tiskt
    1.40
     cristiana
    1.23
     griega
    1.20
    いたしました
    1.20
     både
    1.19
    faring
    1.17
    なのですが
    1.15
    しております
    1.15
    plets
    1.13
    Activations Density 0.015%

    No Known Activations