© 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. 81656
    Prev
    Next
    INDEX
    Explanations

    exoplanets and planets

    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
     attore
    -0.69
     absorbent
    -0.68
     Klar
    -0.68
    ۰
    -0.67
     longueur
    -0.66
    ‌لار
    -0.66
     обрабаты
    -0.66
     getSource
    -0.65
     tableaux
    -0.64
    (!_
    -0.64
    POSITIVE LOGITS
     planets
    1.44
     planet
    1.13
     Extras
    1.05
    extras
    1.02
    exo
    1.00
    Extras
    0.98
     ex
    0.96
     Exo
    0.96
     exo
    0.93
     transit
    0.91
    Activations Density 0.046%

    No Known Activations