© 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. 210722
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions linking phrases

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

    words ending in suffixes like ation

    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
    達成
    0.48
     devast
    0.45
     エ
    0.44
    とにかく
    0.43
    見積
    0.43
     ディ
    0.42
    問
    0.42
     feared
    0.41
     hailed
    0.41
     angst
    0.41
    POSITIVE LOGITS
     vermiş
    0.61
     २
    0.51
     राजपूत
    0.50
    账户
    0.48
    的空间
    0.48
     kurulum
    0.48
     nasıl
    0.47
     dataGenerator
    0.47
     hayvan
    0.46
     网络
    0.46
    Activations Density 0.001%

    No Known Activations