© 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. 22-GEMMASCOPE-RES-131K
    7. 67900
    Prev
    Next
    INDEX
    Explanations

    equivalent of, analog of, counterpart of

    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_22/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
     defekt
    -1.07
    ۱۲
    -0.96
    ADDITIONAL
    -0.95
    رنگ
    -0.94
     Utilisez
    -0.89
     usta
    -0.89
    noinspection
    -0.88
     etap
    -0.88
     poliéster
    -0.88
    }$
    -0.88
    POSITIVE LOGITS
     equivalent
    1.73
     Equivalent
    1.59
    Equivalent
    1.38
     equivalents
    1.34
    equivalent
    1.27
     counterpart
    1.16
    相当于
    1.11
     having
    1.02
     équi
    1.00
    就像是
    0.99
    Activations Density 0.040%

    No Known Activations