© 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. 76254
    Prev
    Next
    INDEX
    Explanations

    superlative descriptions

    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
    :
    -1.41
    着一个
    -1.24
     alcuni
    -1.07
     bienfaits
    -1.04
    側は
    -1.04
    pretation
    -1.02
     alcune
    -1.02
    着一
    -1.02
    ôtel
    -1.02
     nazis
    -1.01
    POSITIVE LOGITS
     pieces
    1.74
     antiguas
    1.38
     types
    1.38
    上がった
    1.38
     environments
    1.33
     ways
    1.30
     końca
    1.28
     tantos
    1.28
     forms
    1.27
     versions
    1.26
    Activations Density 0.085%

    No Known Activations