© 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. 143792
    Prev
    Next
    INDEX
    Explanations

    common following tokens

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

    DDoS attacks, abandoned buildings, kids

    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
     基于
    0.44
     inconclusive
    0.42
     berdasarkan
    0.41
    ኦ
    0.41
     clandestine
    0.40
    タグ
    0.40
     iconography
    0.38
    团
    0.38
     basing
    0.37
     doctrina
    0.37
    POSITIVE LOGITS
     सगळ्या
    0.54
     istedi
    0.49
    喜び
    0.46
    😍
    0.46
    ጥነት
    0.45
     😍
    0.44
     неви
    0.43
    💚
    0.43
    চ্ছন্দ
    0.43
    🤩
    0.43
    Activations Density 0.000%

    No Known Activations