© 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. 26339
    Prev
    Next
    INDEX
    Explanations

    former, earlier, initial

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

    preceded by conjunctions or punctuation

    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
    งาน
    0.34
    grandchildren
    0.34
    男女
    0.33
    ध्
    0.33
    잼
    0.32
    罗斯
    0.32
    ungsver
    0.32
    🎧
    0.31
    af
    0.31
    瑜
    0.30
    POSITIVE LOGITS
     earlier
    0.39
     preceding
    0.37
    前者
    0.36
     former
    0.34
     initial
    0.33
     predecessor
    0.32
     Earlier
    0.32
     Jind
    0.31
     бывшего
    0.31
     starters
    0.30
    Activations Density 0.127%

    No Known Activations