© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98148
    Prev
    Next
    INDEX
    Explanations

    perhaps introducing notable characteristics

    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
    probably
    -1.92
     probabilmente
    -1.80
     probably
    -1.69
     probablement
    -1.55
    Probably
    -1.48
     vielleicht
    -1.44
    とにかく
    -1.43
     prolly
    -1.43
    perhaps
    -1.41
     absolut
    -1.35
    POSITIVE LOGITS
     more
    2.09
     best
    1.83
     most
    1.70
     even
    1.59
     one
    1.55
     bäst
    1.48
     only
    1.48
     the
    1.48
     less
    1.46
     not
    1.38
    Activations Density 0.036%

    No Known Activations