© 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. 180906
    Prev
    Next
    INDEX
    Explanations

    after conjunctions or prepositions

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

    legal and educational terms

    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
    Portuguese
    0.49
    codingPath
    0.48
    řed
    0.46
    獠
    0.46
     işlemler
    0.46
    abyrinth
    0.45
    RPG
    0.44
     سعودی
    0.44
    irting
    0.44
    可以看到
    0.44
    POSITIVE LOGITS
    잖아요
    0.52
     infinitesimal
    0.50
     Buckley
    0.43
    ₀
    0.43
     Doyle
    0.41
     Embry
    0.41
     Trio
    0.41
     embry
    0.40
     стоя
    0.40
     interfered
    0.40
    Activations Density 0.001%

    No Known Activations