© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2927
    Prev
    Next
    INDEX
    Explanations

    punctuation or conjunction followed by 'all' or 'and'

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

    produced in

    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_53_width_65k_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
    ե
    0.34
    妽
    0.33
    ธ
    0.33
    empo
    0.32
     ندار
    0.32
     शर्तों
    0.32
    ක
    0.32
    ཁ
    0.31
    arlene
    0.31
    ikleri
    0.30
    POSITIVE LOGITS
    .”.
    0.40
    ﹐
    0.39
     ……..
    0.37
     …….
    0.37
     offenbar
    0.37
    ”,
    0.37
    ।”
    0.36
    .”)
    0.36
     […]
    0.35
     ude
    0.35
    Activations Density 0.320%

    No Known Activations