© 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. 38062
    Prev
    Next
    INDEX
    Explanations

    zodiac signs and constellations

    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
    !")
    -0.77
    LocalDate
    -0.77
     studenti
    -0.76
     broderie
    -0.74
    laka
    -0.74
     Majest
    -0.73
    ән
    -0.72
    開口
    -0.72
    轎
    -0.71
     smartphone
    -0.71
    POSITIVE LOGITS
     Leo
    1.20
     Cancer
    1.20
     Capricorn
    1.16
     Virgo
    1.15
     Aries
    1.13
    Cancer
    1.06
     Scorpio
    1.06
     Aquarius
    1.04
     Gemini
    1.04
     Pisces
    0.97
    Activations Density 0.012%

    No Known Activations