© 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. 234873
    Prev
    Next
    INDEX
    Explanations

    sports substitutions, predatory, hero, books

    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
    컷
    0.47
    debounce
    0.46
    水的
    0.43
    Disable
    0.43
     দুষ্ট
    0.42
    ন্যাশনাল
    0.42
    捺
    0.42
    дал
    0.42
    덩
    0.41
    ineux
    0.41
    POSITIVE LOGITS
     години
    0.47
     hver
    0.45
    orpions
    0.45
    ffiti
    0.44
     ſt
    0.44
     ۳
    0.44
     لم
    0.43
    lets
    0.43
    jä
    0.42
    ämme
    0.42
    Activations Density 0.000%

    No Known Activations