© 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. 106620
    Prev
    Next
    INDEX
    Explanations

    skulls and remembrance

    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
     cambios
    -0.91
    izacin
    -0.87
    raeli
    -0.85
     suivent
    -0.84
    ARKS
    -0.83
     Cheesecake
    -0.83
     primavera
    -0.81
     BIRTHDAY
    -0.79
    スタム
    -0.78
    赈
    -0.77
    POSITIVE LOGITS
     skulls
    1.05
     departed
    1.03
     deceased
    1.02
     November
    0.96
     skull
    0.94
    亡
    0.93
     novembro
    0.92
     Deceased
    0.91
     remembering
    0.90
    November
    0.89
    Activations Density 0.004%

    No Known Activations