© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11571
    Prev
    Next
    INDEX
    Explanations

    physcomitrella, stuart, brent, liverworts

    np_acts-logits-general · gemini-2.5-flash-lite

    moss and spores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ofType
    0.39
     contag
    0.38
    𝜇
    0.38
    ObjectId
    0.37
    bins
    0.37
    otopy
    0.37
     Luz
    0.36
    <tr>
    0.36
     nations
    0.36
     thirties
    0.35
    POSITIVE LOGITS
     букмекер
    0.48
     কাপড়
    0.45
     বিস্তারিত
    0.44
     elaborar
    0.41
    詳
    0.40
     Merchandise
    0.40
     Dewan
    0.40
     রাস্ত
    0.40
    譴
    0.39
    iegend
    0.39
    Activations Density 0.006%

    No Known Activations