© 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. 129600
    Prev
    Next
    INDEX
    Explanations

    image references

    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
     that
    -1.98
    </h5>
    -1.30
    こう
    -1.26
    </h4>
    -1.26
     also
    -1.19
     Nachmittag
    -1.19
    otropy
    -1.13
     gewüns
    -1.10
     KeyError
    -1.10
    ,
    -1.10
    POSITIVE LOGITS
    મે
    1.35
    いかがでしたか
    1.33
    hradun
    1.30
    爆笑
    1.27
     saiba
    1.24
     péro
    1.23
     podremos
    1.23
     "...
    1.23
     запро
    1.17
     pensez
    1.17
    Activations Density 0.011%

    No Known Activations