© 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. 10-GEMMASCOPE-RES-131K
    7. 71008
    Prev
    Next
    INDEX
    Explanations

    academic and political figures

    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_10/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
     bekannt
    -1.24
     Cependant
    -1.19
     znan
    -1.16
     lojas
    -1.16
    ekwondo
    -1.16
     alemão
    -1.15
     chilen
    -1.13
    徳島
    -1.12
     élégante
    -1.12
     elegantes
    -1.11
    POSITIVE LOGITS
     also
    1.34
     this
    1.33
    这种
    1.23
     how
    1.20
     years
    1.15
     try
    1.15
     those
    1.13
     Feind
    1.09
     ġ
    1.06
     legen
    1.05
    Activations Density 0.069%

    No Known Activations