© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15068
    Prev
    Next
    INDEX
    Explanations

    words suggesting difficulty or negative qualities

    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_16k_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
    ®,
    0.15
    萨
    0.15
    美国
    0.15
    푅
    0.14
    纽约
    0.14
    ஸ்
    0.14
    Argonne
    0.14
     biomed
    0.13
    镛
    0.13
     الغذ
    0.13
    POSITIVE LOGITS
     Brexit
    0.14
     Schengen
    0.14
     betray
    0.13
     encroach
    0.13
     der
    0.13
     reden
    0.13
     reproach
    0.12
     Decreto
    0.12
     riot
    0.12
     নিষ্ঠুর
    0.12
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.