© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117451
    Prev
    Next
    INDEX
    Explanations

    birth location and date

    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
     it
    -0.97
     each
    -0.86
     Rückseite
    -0.82
    结论
    -0.81
     such
    -0.78
     終
    -0.76
     بعض
    -0.76
    皰
    -0.75
     target
    -0.74
     mercados
    -0.73
    POSITIVE LOGITS
     nationality
    1.11
     zodiac
    1.08
     ethnicity
    0.91
    ɑ
    0.89
    าร์
    0.89
     plafon
    0.86
     postcode
    0.86
     Caucasian
    0.86
     mixte
    0.86
     horoscope
    0.85
    Activations Density 0.020%

    No Known Activations