© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 36263
    Prev
    Next
    INDEX
    Explanations

    a quote, civil aviation, a price

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

    regularly / frequently

    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_31_width_262k_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
     the
    0.52
    这个
    0.51
     glorie
    0.49
     thei
    0.48
     Fintech
    0.47
     this
    0.46
     Iconic
    0.44
    漑
    0.44
     fintech
    0.44
    তই
    0.43
    POSITIVE LOGITS
     sním
    0.56
     effectuées
    0.50
     regelmäßig
    0.47
     soal
    0.46
     Versorgung
    0.46
    த்துடன்
    0.45
     dgn
    0.45
     benzer
    0.44
     войска
    0.43
    troops
    0.43
    Activations Density 0.000%

    No Known Activations