© 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. 34-GEMMASCOPE-RES-131K
    7. 7038
    Prev
    Next
    INDEX
    Explanations

    counterpart or equivalents

    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_34/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
    誰
    -0.87
    GITHUB
    -0.86
    iencia
    -0.82
    árqu
    -0.81
     amélior
    -0.81
     Himself
    -0.77
    âtel
    -0.76
     υπάρχ
    -0.76
     сама
    -0.74
    PLING
    -0.73
    POSITIVE LOGITS
     counterpart
    6.81
     counterparts
    6.34
     equivalents
    3.58
     equivalent
    3.31
    equivalent
    2.75
     analogues
    2.61
    counter
    2.59
     analogue
    2.52
    Equivalent
    2.41
     Equivalent
    2.38
    Activations Density 0.165%

    No Known Activations