© 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. 59293
    Prev
    Next
    INDEX
    Explanations

    license notices and code comments

    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
     mientras
    -0.91
     aquí
    -0.77
    Père
    -0.76
     ahora
    -0.75
     Couleur
    -0.74
    力气
    -0.74
     Réalisation
    -0.72
    follows
    -0.71
     new
    -0.71
     द
    -0.71
    POSITIVE LOGITS
    UnknownFields
    0.97
     notice
    0.96
     notices
    0.93
     cómics
    0.88
     Notices
    0.88
    notice
    0.88
     propositions
    0.83
     noticed
    0.83
    fă
    0.82
     佛
    0.82
    Activations Density 0.003%

    No Known Activations