© 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. 642
    Prev
    Next
    INDEX
    Explanations

    conditional clauses and punctuation

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

    distant, remote

    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
    鲔
    0.35
    لد
    0.30
    柽
    0.30
    헙
    0.29
     stets
    0.29
    的数据
    0.29
    缐
    0.29
     Zeich
    0.28
     منهج
    0.28
    峤
    0.28
    POSITIVE LOGITS
    就算是
    0.41
    如果
    0.38
    哪怕
    0.37
    ——
    0.36
     hehe
    0.36
    只是
    0.36
    既然
    0.34
    hehe
    0.34
    如果是
    0.33
    到时候
    0.32
    Activations Density 0.050%

    No Known Activations