© 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. 123887
    Prev
    Next
    INDEX
    Explanations

    defending him, history of, align center

    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
    ᚔ
    -2.09
    蓠
    -1.75
     colorear
    -1.63
     sonre
    -1.59
     Issus
    -1.55
    苤
    -1.52
     desear
    -1.52
    粜
    -1.50
    糨
    -1.50
    KommentareTeilen
    -1.49
    POSITIVE LOGITS
     by
    2.84
     these
    2.66
     on
    2.64
     this
    2.48
     when
    2.47
     then
    2.16
     or
    2.00
     those
    1.82
     such
    1.76
    when
    1.75
    Activations Density 0.235%

    No Known Activations