© 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. 172365
    Prev
    Next
    INDEX
    Explanations

    born after

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

    simply put

    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
     médias
    0.49
    띄
    0.47
    აგ
    0.47
    刊
    0.45
    ští
    0.44
     témoins
    0.44
    পাকিস্তানের
    0.44
    やかな
    0.44
    媒體
    0.44
    ᅮ
    0.43
    POSITIVE LOGITS
     Maths
    0.48
     يعتبر
    0.45
    a
    0.45
     Jeep
    0.44
     Router
    0.43
     esperado
    0.42
     الك
    0.41
     Teams
    0.41
    alyse
    0.41
    OrElse
    0.41
    Activations Density 0.001%

    No Known Activations