© 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. 68071
    Prev
    Next
    INDEX
    Explanations

    under the License

    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
     valued
    -1.52
     optar
    -1.48
     personalizar
    -1.43
     privately
    -1.40
    躥
    -1.39
     EXPLANATION
    -1.37
     SPANISH
    -1.37
    臯
    -1.36
     anyone
    -1.36
     invested
    -1.35
    POSITIVE LOGITS
     cocky
    1.38
     salvajes
    1.32
     of
    1.31
    :
    1.30
     étrange
    1.29
    Lähde
    1.29
     berakhir
    1.28
     néhány
    1.25
     például
    1.24
    ः
    1.22
    Activations Density 0.426%

    No Known Activations