© 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. 10-GEMMASCOPE-RES-131K
    7. 19936
    Prev
    Next
    INDEX
    Explanations

    time, currently, friend, both

    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
     will
    -1.51
     on
    -1.44
    reportWebVitals
    -1.39
    ”,
    -1.38
     dirancang
    -1.34
     at
    -1.32
     presentará
    -1.28
     new
    -1.27
    </td>
    -1.27
    },
    -1.26
    POSITIVE LOGITS
     enfri
    1.27
    verige
    1.23
     mikrofon
    1.23
     existant
    1.20
     these
    1.20
     그것
    1.20
     armados
    1.20
    焢
    1.19
     ilgi
    1.19
     it
    1.17
    Activations Density 0.724%

    No Known Activations