© 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. 194115
    Prev
    Next
    INDEX
    Explanations

    words following article or noun

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

    subscribing or negative contraction

    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
     Афри
    0.43
     हल्ला
    0.43
     ধ্ব
    0.42
    ssel
    0.42
     வாங்கி
    0.42
    sto
    0.41
     difficulties
    0.41
    🐔
    0.41
    ificar
    0.41
     विजयी
    0.40
    POSITIVE LOGITS
    Check
    0.46
     rec
    0.46
    可在
    0.45
    Police
    0.45
     tibia
    0.45
     ascor
    0.44
     cilvē
    0.43
    控件
    0.43
    ocytic
    0.43
     sider
    0.43
    Activations Density 0.003%

    No Known Activations