© 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. 40606
    Prev
    Next
    INDEX
    Explanations

    Rituximab, Ritchey, rhythmic, pitfalls, Magnum

    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
    昞
    -2.66
     arduous
    -2.63
    \
    -2.55
    翃
    -2.47
     наша
    -2.47
     včetně
    -2.47
     großer
    -2.44
    騖
    -2.36
    倻
    -2.34
     proverbial
    -2.33
    POSITIVE LOGITS
    </strong>
    2.86
     was
    2.64
     concorda
    2.52
    同时也
    2.45
     recompensa
    2.45
    <td>
    2.39
     Their
    2.38
     It
    2.36
    AM
    2.36
    」
    2.34
    Activations Density 0.016%

    No Known Activations