© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99591
    Prev
    Next
    INDEX
    Explanations

    soul and its common follow-on words

    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
    之后的
    -0.96
    过后
    -0.95
    脑袋
    -0.94
     월
    -0.86
     پلیس
    -0.85
    Servicios
    -0.82
    的不同
    -0.82
    ▍
    -0.82
    頭を
    -0.82
     faults
    -0.81
    POSITIVE LOGITS
     Soul
    1.26
     soul
    1.22
    Soul
    1.20
    mates
    1.17
     mate
    1.08
     soulful
    1.08
    1.02
    matism
    1.02
     Searching
    1.01
    中共
    1.00
    Activations Density 0.005%
    No Known Activations