© 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. 14604
    Prev
    Next
    INDEX
    Explanations

    concessions and their positive outcomes

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

    Luck, aided, lucky, specific

    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
    COLUMN
    0.44
     conflicting
    0.43
    を示
    0.40
     değeri
    0.40
     появление
    0.39
    刖
    0.38
    Collegamenti
    0.37
    袭
    0.37
    妒
    0.37
    |}\
    0.37
    POSITIVE LOGITS
     aided
    0.58
     shielded
    0.55
     bolstered
    0.55
     cushioned
    0.54
     clever
    0.54
     fortunate
    0.52
     lucky
    0.52
     compensated
    0.51
     luckily
    0.50
     sheltered
    0.50
    Activations Density 0.609%

    No Known Activations