© 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. 112133
    Prev
    Next
    INDEX
    Explanations

    propose, claim, contend

    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
    </strong>
    -2.00
    </h2>
    -1.76
     francus
    -1.66
     Елена
    -1.33
    sejarah
    -1.29
     bonté
    -1.28
     sportowe
    -1.27
    </tfoot>
    -1.25
     delikat
    -1.24
     programu
    -1.23
    POSITIVE LOGITS
     vost
    1.38
    也是
    1.30
     intoxic
    1.29
     construc
    1.23
     novi
    1.23
     therefore
    1.23
     introd
    1.23
     asim
    1.22
     erit
    1.22
     ork
    1.22
    Activations Density 0.043%

    No Known Activations