© 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. 104861
    Prev
    Next
    INDEX
    Explanations

    following the word "we"

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

    geometric patterns and colors

    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
    仨
    0.56
     थ्री
    0.53
    వీ
    0.48
     ketiga
    0.47
    ޯ
    0.46
    สาม
    0.44
    ेटिव
    0.43
     threes
    0.43
     Backup
    0.43
    챈
    0.42
    POSITIVE LOGITS
    ureen
    0.46
    ರ್ಷ
    0.45
     conclusively
    0.45
     লক্ষ
    0.43
    ţi
    0.43
    цна
    0.43
    то
    0.42
     대신
    0.42
    faq
    0.42
    HAO
    0.42
    Activations Density 0.000%

    No Known Activations