© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 210172
    Prev
    Next
    INDEX
    Explanations

    collection containing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    らが
    0.44
    ск
    0.42
    шуу
    0.41
     Б
    0.38
     SaaS
    0.38
    <0xA7>
    0.38
    зик
    0.38
     পরিস্থিতির
    0.37
    ничный
    0.37
     सा
    0.37
    POSITIVE LOGITS
     pref
    0.41
     contemplating
    0.39
    exports
    0.39
     perf
    0.39
     equ
    0.39
    ?”
    0.38
     Tv
    0.38
    严重
    0.38
     severe
    0.37
    ”
    0.37
    Activations Density 0.002%

    No Known Activations