© 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. 164659
    Prev
    Next
    INDEX
    Explanations

    news and positive descriptions

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

    societal trends and expectations

    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
     prophylaxis
    0.59
     sais
    0.52
     extensible
    0.48
     prophyl
    0.48
     prophylactic
    0.43
     ipv
    0.42
    飲
    0.41
     polymerized
    0.41
     polymerization
    0.41
     protrusion
    0.40
    POSITIVE LOGITS
     അഭിപ്
    0.59
    鸫
    0.54
     वायरिंग
    0.48
     Indoor
    0.47
     ജ
    0.46
    影响力
    0.46
    Cheerful
    0.45
     मैंने
    0.45
     एक्सप्लेन
    0.45
    ਜੀ
    0.45
    Activations Density 0.002%

    No Known Activations