© 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. 31-GEMMASCOPE-2-RES-262K
    4. 56912
    Prev
    Next
    INDEX
    Explanations

    web analytics and auditing

    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_31_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
    하거나
    0.40
     causative
    0.40
     또는
    0.40
     ಅಥವಾ
    0.40
     ἢ
    0.40
    сро
    0.39
    或者是
    0.39
    見える
    0.39
    거나
    0.38
    あるいは
    0.38
    POSITIVE LOGITS
     intelekt
    0.51
     fasilitas
    0.45
    RefCount
    0.44
     ዘዴ
    0.44
     obchod
    0.43
     عمليه
    0.43
    𝖊
    0.43
     bisnis
    0.42
     estat
    0.42
     сын
    0.42
    Activations Density 0.003%

    No Known Activations