© 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. 102702
    Prev
    Next
    INDEX
    Explanations

    access allowed

    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
     desgaste
    -0.73
     맞
    -0.67
     tune
    -0.66
     centroid
    -0.66
    の情報
    -0.63
     deliciosa
    -0.63
    ⠝
    -0.63
     rilev
    -0.62
    Propagation
    -0.62
     prosecuted
    -0.61
    POSITIVE LOGITS
     نگه
    0.74
     canlı
    0.73
     Schott
    0.71
     boast
    0.69
     vào
    0.69
     extractor
    0.68
     Corpus
    0.68
     situés
    0.66
    Palo
    0.65
     scorn
    0.65
    Activations Density 0.044%

    No Known Activations