© 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. 71307
    Prev
    Next
    INDEX
    Explanations

    "," said"," says"," declared"," answered"," he"," she"," Al"," Andrew"," productivity

    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
     sogenannte
    -1.68
    いえば
    -1.68
    ਃ
    -1.63
    begin
    -1.63
    そして
    -1.63
     größere
    -1.61
    ちなみに
    -1.60
     circumvent
    -1.53
     refurb
    -1.52
    okkal
    -1.52
    POSITIVE LOGITS
     which
    1.76
     but
    1.59
    附近
    1.57
    ,"
    1.55
    為に
    1.52
     because
    1.52
     before
    1.48
     wystarczy
    1.48
     changed
    1.47
     fossero
    1.44
    Activations Density 0.016%

    No Known Activations