© 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. 107508
    Prev
    Next
    INDEX
    Explanations

    practice

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

    RGBA images

    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
    毕业
    0.50
    切换
    0.46
    ುವುದ
    0.46
    职位
    0.46
     Kelas
    0.46
    详
    0.45
    囘
    0.45
    小說
    0.45
    Readme
    0.44
    砌
    0.44
    POSITIVE LOGITS
     manicure
    0.63
     parquet
    0.56
     tableware
    0.53
     comen
    0.52
     paves
    0.52
     caucasian
    0.51
     taxa
    0.50
     comest
    0.50
     radiant
    0.50
     possible
    0.50
    Activations Density 0.001%

    No Known Activations